CN113553763A - Tunnel surrounding rock rapid grading method and system - Google Patents
Tunnel surrounding rock rapid grading method and system Download PDFInfo
- Publication number
- CN113553763A CN113553763A CN202110785371.5A CN202110785371A CN113553763A CN 113553763 A CN113553763 A CN 113553763A CN 202110785371 A CN202110785371 A CN 202110785371A CN 113553763 A CN113553763 A CN 113553763A
- Authority
- CN
- China
- Prior art keywords
- rock
- grading
- data
- index
- tunnel
- 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
- 239000011435 rock Substances 0.000 title claims abstract description 196
- 238000000034 method Methods 0.000 title claims abstract description 77
- 238000012937 correction Methods 0.000 claims abstract description 50
- 238000012360 testing method Methods 0.000 claims abstract description 31
- 238000013528 artificial neural network Methods 0.000 claims abstract description 27
- 238000012545 processing Methods 0.000 claims abstract description 10
- 238000007405 data analysis Methods 0.000 claims abstract description 9
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 18
- 230000008569 process Effects 0.000 claims description 14
- 239000003673 groundwater Substances 0.000 claims description 11
- 238000004364 calculation method Methods 0.000 claims description 10
- 239000011159 matrix material Substances 0.000 claims description 10
- 238000010606 normalization Methods 0.000 claims description 10
- 238000009412 basement excavation Methods 0.000 claims description 9
- 238000005457 optimization Methods 0.000 claims description 9
- 238000005516 engineering process Methods 0.000 claims description 8
- 238000005259 measurement Methods 0.000 claims description 6
- 238000011161 development Methods 0.000 claims description 4
- 238000002310 reflectometry Methods 0.000 claims description 4
- 238000006073 displacement reaction Methods 0.000 claims description 3
- 230000002093 peripheral effect Effects 0.000 claims description 3
- 238000010276 construction Methods 0.000 abstract description 7
- 239000010410 layer Substances 0.000 description 52
- 230000000694 effects Effects 0.000 description 3
- 238000007781 pre-processing Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000009499 grossing Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 229920006395 saturated elastomer Polymers 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002457 bidirectional effect Effects 0.000 description 1
- 238000012669 compression test Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005315 distribution function Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 239000002344 surface layer Substances 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B21/00—Measuring arrangements or details thereof, where the measuring technique is not covered by the other groups of this subclass, unspecified or not relevant
- G01B21/16—Measuring arrangements or details thereof, where the measuring technique is not covered by the other groups of this subclass, unspecified or not relevant for measuring distance of clearance between spaced objects
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N3/00—Investigating strength properties of solid materials by application of mechanical stress
- G01N3/02—Details
- G01N3/06—Special adaptations of indicating or recording means
- G01N3/068—Special adaptations of indicating or recording means with optical indicating or recording means
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N3/00—Investigating strength properties of solid materials by application of mechanical stress
- G01N3/40—Investigating hardness or rebound hardness
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N3/00—Investigating strength properties of solid materials by application of mechanical stress
- G01N3/62—Manufacturing, calibrating, or repairing devices used in investigations covered by the preceding subgroups
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
-
- 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
- G06N3/045—Combinations of networks
-
- 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
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2203/00—Investigating strength properties of solid materials by application of mechanical stress
- G01N2203/0014—Type of force applied
- G01N2203/0016—Tensile or compressive
- G01N2203/0019—Compressive
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2203/00—Investigating strength properties of solid materials by application of mechanical stress
- G01N2203/0058—Kind of property studied
- G01N2203/0076—Hardness, compressibility or resistance to crushing
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2203/00—Investigating strength properties of solid materials by application of mechanical stress
- G01N2203/02—Details not specific for a particular testing method
- G01N2203/0202—Control of the test
- G01N2203/0212—Theories, calculations
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2203/00—Investigating strength properties of solid materials by application of mechanical stress
- G01N2203/02—Details not specific for a particular testing method
- G01N2203/06—Indicating or recording means; Sensing means
- G01N2203/0641—Indicating or recording means; Sensing means using optical, X-ray, ultraviolet, infrared or similar detectors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Immunology (AREA)
- Analytical Chemistry (AREA)
- Pathology (AREA)
- Biochemistry (AREA)
- Chemical & Material Sciences (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Probability & Statistics with Applications (AREA)
- Medical Informatics (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Manufacturing & Machinery (AREA)
- Geophysics And Detection Of Objects (AREA)
Abstract
The invention discloses a method and a system for rapidly grading tunnel surrounding rocks, wherein the method comprises the following steps: determining a rapid surrounding rock grading index; testing the integrity index of the rock mass; testing the rock hardness degree index; determining a correction index; rapidly judging the grade of the surrounding rock according to the index value based on the neural network; outputting a judgment result; a rapid grading system for tunnel surrounding rocks comprises: the device comprises an acquisition module, a data processing module, a data analysis module and an output module; the acquisition module acquires data through hardware equipment; the data processing module comprises morphology data, laser echo data and correction data; the data analysis module analyzes by constructing a neural network; the output module comprises a terminal and a cloud server; the method can accurately and quickly grade the surrounding rock, and can ensure the accuracy of judgment through the neural network; different surrounding rocks can be rapidly and automatically graded, so that the construction cost is effectively reduced; the working efficiency can be effectively improved, and the working period is shortened.
Description
Technical Field
The invention relates to the field of tunnel engineering, in particular to a method and a system for quickly grading surrounding rocks of a tunnel.
Background
The rapid grading of the tunnel surrounding rocks is the premise of realizing reasonable and accurate supporting design and guaranteeing the safety of field construction. According to the classification standard of engineering rock mass, the basic classification of surrounding rock can be determined by the hardness degree of rock and the integrity degree of rock mass. The hardness degree of the rock can be determined by the uniaxial saturation compressive strength, and the integrity degree of the rock is divided according to an integrity index. Obviously, the traditional division method needs to be realized according to an indoor rock test, and has long judgment period and low efficiency.
With the development of scanning technologies such as three-dimensional morphology and three-dimensional laser, the efficiency, portability and accuracy of the equipment are continuously improved. The technology can not only acquire the space point cloud data information of a scanning object and identify the physical appearance characteristics of a target body, but also measure the mechanical strength performance by detecting the laser echo of the target object. Therefore, the scanning equipment and the scanning technology can be effectively applied to geological work.
As the traditional surrounding rock grading method utilizes indoor rock compression test, engineering geophysical prospecting test, on-site geological survey and other methods, although the methods can grade the surrounding rock, the method has the defects of high construction cost, long working period and low efficiency. The three-dimensional scanning technology is combined into the classification work of the surrounding rocks of the tunnel, and the working period of the classification work of the surrounding rocks can be effectively reduced on the premise of ensuring the classification judgment accuracy of the surrounding rocks, so that the rapid surrounding rock grade judgment method and the software and hardware system have great significance for tunnel construction.
Disclosure of Invention
The invention aims to: aiming at the existing problems, a method and a system for rapidly grading tunnel surrounding rocks are provided; the invention solves the problem of high cost of surrounding rock grading construction; the problem of low grading efficiency is solved.
The technical scheme adopted by the invention is as follows:
a method for rapidly grading tunnel surrounding rocks comprises the following steps: determining a rapid surrounding rock grading index; testing the integrity index of the rock mass; testing the rock hardness degree index; determining a correction index; rapidly judging the grade of the surrounding rock according to the index value based on the neural network; and outputting the judgment result.
Further, the determined grading index is obtained by analyzing a common tunnel surrounding rock grading basic theory method; the common tunnel surrounding rock classification basic theory method comprises RMR, Q, RMi, GSI and BQ.
Further, the method for testing the integrity index of the rock mass comprises the following steps: obtaining three-dimensional space point cloud data of target surrounding rocks by adopting a three-dimensional geological scanning technology, calculating the joint number and the joint distance of the rocks, further calculating the joint number Jv in each cubic meter of rocks, and obtaining rock integrity indexes Kv according to a standard recommendation table; the Jv is calculated by
Wherein JvIs the volume adjustment number of rock mass, SiNumber of lines on 1m measuring line for group joint, S0Is 1m3The rock mass is not the number of the joints in groups.
Further, the method for testing the rock hardness degree index comprises the following steps: calibrating the laser echo intensity of the surrounding rock and the uniaxial compressive strength of the rock mass into a functional relation, and estimating the compressive strength of the rock by using the scanned laser echo intensity of the rock mass;
the laser echo intensity calculation method comprises
Wherein E isiTransmitting signal intensity for the laser radar; etasysIs a system parameter; etaatmIs an atmospheric influence factor; drIs the lidar receiving aperture;
as a function of the dichroic reflectivity profile; thetaiIs the laser incident angle;
is the incident azimuth angle; thetasIs the laser exit angle;
is the backscatter azimuth; rdIs the distance between the target and the lidar system;
the function relation is Rc＝Ax+B，RcThe uniaxial compressive strength of the rock mass, x the laser echo strength of the surrounding rock, and A and B are coefficients.
Further, the correction index comprises a groundwater influence correction coefficient K1Correction coefficient K for attitude influence of main structural plane2Initial stress state influence correction coefficient K3；
The method for rapidly determining the groundwater influence correction coefficient comprises the following steps: observing the water outlet state of the tunnel face and the peripheral wall of the tunnel; selecting and determining the type of the water outlet state; water pressure test or water yield test; looking up a table to determine a correction coefficient;
the method for rapidly determining the attitude influence correction coefficient of the main structural surface comprises the following steps: measuring the inclination angle and the inclination of the main structural surface and the trend of the tunnel by using an electronic geological compass, identifying the included angle between the main structural surface and the trend of the tunnel and the inclination angle of the structural surface, sequentially solving the influence coefficient if a plurality of weak structural surfaces exist, and taking the maximum value;
the method for quickly determining the influence correction coefficient of the initial stress state comprises the following steps: lithological texture identification, wherein the lithological texture belongs to hard rock or soft rock; if the rock is hard rock, observing and recording the symbolic phenomenon of rock burst in the excavation process; if the rock is soft rock, observing and recording the marking phenomenon of core caking in the excavation process; recording the stripping and displacement of the cave wall rock mass and the development condition of a new crack in the excavation process; the table lookup determines the correction factor.
Further, the method for rapidly judging the surrounding rock grade according to the index value based on the neural network comprises the following steps: dividing the surrounding rock information transmitted to the cloud end in each field actual measurement into three types of a, b and c, wherein a represents the uniaxial compressive strength R of the rock masscB represents the rock integrity index KvC represents the correction factor K1+K2+K3To obtain a data set of a, b, and c, which is used to construct the neural network.
Further, the neural network structure includes: inputting a layer, representing coordinate values of the surrounding rock information; the hidden layer represents an algorithm from the surrounding rock information to an output result and comprises two n-dimensional matrixes; the output layer is used for controlling the output layer into a matrix of 1 x 5 through two n-dimensional matrixes of the hidden layer, and grading is carried out through the matrix; the output result normalization layer is used for increasing the accuracy of grading; the back propagation and parameter optimization layer is used for quantifying the quality of the output result normalization layer; and the iteration layer is used for improving the probability of outputting the result.
A rapid grading system for tunnel surrounding rocks applying the method of claim 1 comprises: the device comprises an acquisition module, a data processing module, a data analysis module and an output module; the acquisition module acquires data through hardware equipment; the data processing module comprises morphology data, laser echo data and correction data; the data analysis module analyzes by constructing a neural network; the output module comprises a terminal and a cloud server.
Further, the hardware device of the acquisition module includes: three-dimensional geological scanners, laser echo testers and electronic compasses.
Further, the neural network structure includes: the device comprises an input layer, a hidden layer, an output layer, a normalization layer, a parameter optimization layer and an iteration layer.
In summary, due to the adoption of the technical scheme, the invention has the beneficial effects that:
1. the method comprises the steps of determining rapid grading indexes of surrounding rocks; testing the integrity index of the rock mass; testing the rock hardness degree index; the correction indexes are determined, so that the surrounding rock can be classified rapidly and accurately, and the judgment accuracy can be guaranteed through a neural network.
2. The invention can rapidly and automatically carry out grading treatment on different surrounding rocks through the grading system, effectively reduces the construction cost, and simultaneously can effectively improve the working efficiency and reduce the working period through the full-automatic operation of the system.
Drawings
The invention will now be described, by way of example, with reference to the accompanying drawings, in which:
fig. 1 is a flow chart of a method for rapidly grading tunnel surrounding rocks.
FIG. 2 is a flow chart of rock integrity index testing.
FIG. 3 is a flow chart of a method for rapid determination of groundwater influence correction factor.
FIG. 4 is a flow chart of a method for determining the attitude impact correction factor for a primary structure plane.
FIG. 5 is an initial stress state determination flow chart.
Fig. 6 is a structure diagram of a rapid tunnel surrounding rock grading system.
Detailed Description
All of the features disclosed in this specification, or all of the steps in any method or process so disclosed, may be combined in any combination, except combinations of features and/or steps that are mutually exclusive.
Any feature disclosed in this specification (including any accompanying claims, abstract) may be replaced by alternative features serving equivalent or similar purposes, unless expressly stated otherwise. That is, unless expressly stated otherwise, each feature is only an example of a generic series of equivalent or similar features.
Example 1
A method for rapidly grading tunnel surrounding rocks, as shown in fig. 1, comprises the following steps:
s1: and determining the rapid grading index of the surrounding rock.
In the method, the classification index is determined by analyzing a common tunnel surrounding rock classification basic theory method; the common tunnel surrounding rock classification basic theory method comprises RMR, Q, RMi, GSI and BQ; in this embodiment, a BQ method is adopted, which is more advantageous in terms of fast determination, and is advantageous in that 1: respectively considering the rock mass quality index and the engineering rock mass quality index; advantage 2: standardizing the corresponding conversion relation of the related key indexes in the given reference table; advantage 3: all indexes have quantitative and qualitative reference modes at the same time of value taking, the quantitative indexes are convenient for quick judgment of a computer, and the qualitative indexes are convenient for later verification of judgment results output by grading equipment.
The basic quality index of the rock mass by the BQ method comprises the saturated uniaxial compressive strength R of the rockcIntegrity level index KvThe quality indexes of the engineering rock mass comprise underground water, a main structural plane and an initial stress state. Wherein the rock saturated uniaxial compressive strength RcThe integrity degree index K is obtained by adopting a laser scanning technologyvThe method is characterized in that a three-dimensional shape scanner is adopted for obtaining, a main structural plane is obtained by an electronic compass, and the quality indexes of the engineering rock mass including underground water and an initial stress state are standardized and qualitative.
S2: and testing the integrity index of the rock mass.
In the steps, firstly, three-dimensional space point cloud data of the target surrounding rock is obtained by adopting a three-dimensional geological scanning technology, the joint number and the joint distance of the rock body are calculated by using matched software, and J is further calculated by the softwarev(number of joints per cubic meter of rock mass),obtaining rock integrity index K according to standard recommendation table 1v。
TABLE 1JvAnd KvCorresponding relationship of
Specifically, as shown in fig. 2, the method includes:
s21: and collecting multi-angle point cloud data.
Because the projection range of the projector, the field range of the camera, the self-shielding limitation of the object and the one-time sampling of the three-dimensional shape scanner can only obtain the information of one side surface of the measured object, the large object needs to be sampled for many times from different angles, and then the integral three-dimensional point cloud is formed by multi-view point cloud splicing and fusion.
S22: and (4) point cloud data preprocessing.
In the measuring process, because a lot of redundant data and partial information loss are inevitably generated in multi-angle sampling, the point cloud data is preprocessed in a denoising and smoothing filtering mode. Denoising, namely automatically removing outlier point clouds in data by software, smoothing data points by a Gaussian filter algorithm, wherein alternative algorithms comprise a median filter method, a mean filter method, a Laplace method, an energy method and an average curvature method, and preprocessing pattern previews under different algorithms are automatically generated by the software in the actual application process and are selected by operators preferentially.
S23: and splicing the multi-view data.
And (3) selecting an integral splicing strategy based on the pose of a certain moving coordinate system, a surface splicing mode and a splicing method based on a moving coordinate measurement system to finish data splicing. Firstly, correspondingly establishing a transformation relation between each unit measurement coordinate system and each unit measurement coordinate system, then unifying the measurement data obtained from different angles to an appointed moving coordinate system (xyz), unifying all the data to a coordinate system (a global common coordinate system), reducing the splicing error between the data, improving the splicing precision and enabling the result to be more ideal; and then, with the unit as a basic unit, constructing a unit geometric shape of the point cloud data of each unit, and splicing the unit geometric shapes to obtain a complete morphology.
S24: and (5) reducing the dimension of the isosurface.
Based on the principle of a grid algorithm, each point cloud data (X) after the multi-view data is splicedi，Yi，Zi) And (2) regarding the element points in the integral grid point set, allocating indexes to each grid by using xyz coordinate values under a global common coordinate system, indexing the edge table according to each grid index, acquiring the edge position (and giving an edge number) of the edge table, recording the point coordinates and the edge number, indexing the connection sequence (the connection sequence is in the form of the edge number) of the points by using each grid index de-indexing line table, and retrieving the coordinate positions of the points from the recorded information by using the edge number. And finally, drawing a connecting line according to the coordinates of all the points.
S25: and (5) cluster division identification.
A contour map is known to be composed of nearly elliptical figures surrounded by a plurality of points of the same height, and the major axis and the minor axis are automatically assigned to each nearly elliptical figure, and the contour map is produced (a)i，bi) Axis data set, aiRepresents the length of the major axis of the ith nearly elliptical pattern, biRepresenting the minor axis length of the ith nearly elliptical pattern, each axis data set corresponding to a height hiCoordinates and deflection angle α of each axisi，hiIs represented by (a)i，bi) Determined depth of joint, alphaiA deflection angle representing the joint is finally formed (a)i，bi，hi，αi) A set of joint data. Dividing the fractures into groups according to the deflection angles by adopting a clustering analysis algorithm, and further identifying the number S of the grouped joints on a 1m measuring lineiAnd number of ungrouped joints S0And then calculating the volume adjustment number of the rock mass according to the following formula:
wherein JvIs the volume adjustment number of rock mass, SiNumber of lines on 1m measuring line for group joint, S0Is 1m3The rock mass is not the number of the joints in groups.
S3: and testing the rock hardness degree index.
In the above steps, the uniaxial compressive strength of the rock mass is estimated according to the laser echo intensity of the surrounding rock so as to determine the rock type. The laser echo intensity of the rock mass has strong correlation with the compressive strength, and when the rock strength is low, a large number of gaps exist in the surface layer and the interior, so that the laser reflection effect is poor, and the reflectivity is low; on the contrary, when the rock strength is higher, the laser reflection effect is better, and the reflectivity is larger. According to the characteristics, the laser echo intensity of the surrounding rock and the uniaxial compressive strength of the rock are calibrated to be in a functional relation, the compressive strength of the rock can be estimated by utilizing the scanned laser echo intensity of the rock, and a corresponding functional form can be adopted according to different lithologies. The laser radar transmits a laser signal to a target, and the laser signal is transmitted back after being scattered by the target.
The lidar measures the distance of the target from time of flight (TOF) and calculates the echo intensity from the received signal. The calculation formula of the echo intensity is as follows:
wherein E isiTransmitting signal intensity for the laser radar; etasysIs a system parameter; etaatmIs an atmospheric influence factor; drIs the lidar receiving aperture;
as a Bidirectional Reflectance Distribution Function (BRDF); thetaiIs the laser incident angle;
is the incident azimuth angle; thetasIs the laser exit angle; theta in lidari＝θs；
Is the backscatter azimuth; rdIs the distance between the target and the lidar system.
The functional form adopted in this embodiment is specifically as follows:
calculating the uniaxial compressive strength of the rock mass according to the correlation between the laser echo strength and the rock mass strength:
Rc＝f(x)
wherein R iscThe uniaxial compressive strength of the rock mass, x the laser echo strength of the surrounding rock and f RcAnd x functional relationship. In general, the uniaxial compressive strength of the rock mass has a simple linear relationship, and can be represented by linear regression:
Rc＝Ax+B
wherein R iscThe uniaxial compressive strength of the rock mass, x, the laser echo strength of the surrounding rock, and A and B are coefficients which are taken according to different lithologies.
The correlation between the echo intensity and the rock intensity is obtained through indoor tests and uploaded to a case library, and as the engineering is continuously promoted, a more accurate conversion relational expression is formed through continuous iterative inversion of a neural network algorithm.
S4: and determining a correction index.
In the above step, the correction index includes a groundwater influence correction coefficient K1Correction coefficient K for attitude influence of main structural plane2Initial stress state influence correction coefficient K3。
In this embodiment, the field quantitative determination of the water pressure and the water inflow amount is complicated, and does not meet the requirement of the rapid test, and it is desirable to directly determine the groundwater influence coefficient by combining the qualitative description about the groundwater state in the specification, so the rapid determination method of the groundwater influence correction coefficient is as shown in fig. 3: s411: observing the water outlet state of the tunnel face and the peripheral wall of the tunnel; s412: selecting and determining the type of the water outlet state; s413: water pressure test or water yield test; s414: the table lookup determines the correction factor. In the table lookup to determine the correction coefficient, the table to be queried is shown in table 2.
TABLE 2 groundwater influence correction factor K1
Wherein p is the fracture water pressure of the surrounding rock, and Q is the water yield of every 10m of the hole.
Correction coefficient K for attitude influence of main structural plane2The determination method of (2) is shown in fig. 4 as follows: s421: measuring the inclination angle and the inclination of the main structural plane and the trend of the tunnel by an electronic geological compass; s422: identifying the included angle between the main structural plane and the tunnel trend and the inclination angle of the structural plane, and if a plurality of weak structural planes exist, solving the influence coefficient K in sequence2And takes the maximum value. The contents of the structural plane attitude and the combination relationship between the structural plane attitude and the hole axis are mainly two contents of the structural plane attitude (inclination angle and trend) test and the hole axis trend test, and the combination relationship is shown in table 3.
TABLE 3 correction factor K for attitude effect of main structural plane2
The main distinguishing contents of the initial ground stress state comprise lithology and texture identification, rock burst marking phenomenon observation, core pie marking phenomenon observation and the like, and the determining process is as shown in figure 5: s431: lithological texture identification, wherein the lithological texture belongs to hard rock or soft rock; s432: if the rock is hard rock, observing and recording the symbolic phenomenon of rock burst in the excavation process; s433: if the rock is soft rock, observing and recording the marking phenomenon of core caking in the excavation process; s434: recording the stripping and displacement of the cave wall rock mass and the development condition of a new crack in the excavation process; s435: determining correction factor K by looking up table3. The lookup table is shown in table 4.
TABLE 4 initial ground stress state influence correction coefficient K3
S5: and rapidly judging the surrounding rock grade according to the index value based on the neural network.
In the steps, the information of the surrounding rocks actually measured on site at each time is divided into three types of a, b and c, wherein a represents the uniaxial compressive strength R of the rock masscB represents the value of the rock integrity indicator Kv and c represents the correction factor (K)1+K2+K3) To obtain a data set of (a, b, c), and constructing a two-layer neural network, wherein the structure of the neural network is as follows:
an input layer: in the set of algorithms, the input layer is a coordinate value (a, b, c) representing the information of the surrounding rock, which is an array containing three data and can also be regarded as a matrix of 1 x 3.
Hiding the layer: the hidden layer represents a set of algorithm from the surrounding rock information (a, b, c) to an output result, and is essentially two n-dimensional matrixes of an input layer-hidden layer and a hidden layer-output layer, corresponding to two matrix operations:
input layer-hidden layer: h ═ X ═ W1+b1
Hidden layer-output layer: y ═ H ═ W2+b2。
An output layer: the output layer is controlled to be a matrix of 1 x 5 through two n-dimensional matrices of the hidden layer, namely, (x, y, z, m, n), x represents I-level surrounding rock, y represents II-level surrounding rock, z represents III-level surrounding rock, m represents IV-level surrounding rock, and n represents V-level surrounding rock, the output matrix result may be (1, -2,3, -4,7), and it is obvious that specific surrounding rock levels cannot be visually displayed, therefore, an active layer is added into the hidden layer, a binary calculation result is output after an activation operation is carried out, namely, (1,0,0, 0), 1 represents the surrounding rock of the current level, and 0 represents the surrounding rock of the non-current level.
An output result normalization layer: according to the algorithm, the purpose of surrounding rock classification is achieved when the calculation is carried out in the last step, but the calculation is not comprehensive enough, and in consideration of the accuracy and the misjudgment rate of the algorithm for surrounding rock classification, a normalization program, namely a Softmax layer, is added behind an output layer, all elements are subjected to exponential powers with e as the base, all exponential powers are summed, and then the exponential powers and the sum are subjected to quotient, so that the calculation formula is as follows:
wherein e is a natural index, and S is a calculated output value.
In the result obtained by the above formula, the sum of all elements is 1, and each element may represent the probability that the surrounding rock to be judged is in a certain level.
Back propagation and parameter optimization layer: after passing through the Softmax layer, we get the probabilities corresponding to the five levels I, II, III, IV and v, respectively, but note that this is the probability value result calculated by the neural network, not the true case. For example, Softmax outputs results of (90%, 5%, 3%, 1%, 1%), and true results of (100%, 0,0,0, 0). Although the output result can be classified correctly, the difference between the output result and the real result is, so the quality of the output result of Softmax needs to be "quantified", and the quantified calculation formula is as follows:
y1＝-logy0
wherein, y0Representing the result element, y, of the output of the "Softmax" layer1Representing the result elements after the quality degree is quantified.
The calculated result value y1The closer to 0, the more accurate the result is, and the output is called "Cross Entropy loss". This "cross-entropy loss" is therefore to be reduced as much as possible when training the neural network.
After the cross entropy loss is calculated, the back propagation and parameter optimization can be realized according to the cross entropy loss generated by using the algorithm to perform surrounding rock classification each time, the optimization objects are W and b in a hidden layer, and the accuracy of surrounding rock judgment can be continuously improved along with the use frequency of the algorithm by continuously optimizing the parameters through the back propagation.
And (3) iteration layer: the neural network is continuously subjected to iterative calculation according to the cross entropy loss of the production by specifying the maximum value of the cross entropy loss until the specified cross entropy loss is reached, and the process can improve the probability of outputting the result.
S6: and outputting the judgment result.
In the above steps, the determination result may be transmitted to a terminal or a cloud server, where the terminal includes a computer or a mobile phone; meanwhile, the terminal can also call data from the cloud server for real-time viewing.
Example 2
A rapid grading system for tunnel surrounding rocks, as shown in fig. 6, comprises: the device comprises an acquisition module, a data processing module, a data analysis module and an output module; the acquisition module acquires data through hardware equipment; the data processing module comprises morphology data, laser echo data and correction data; the data analysis module analyzes by constructing a neural network; the output module comprises a terminal and a cloud server.
The hardware equipment of the acquisition module comprises: the three-dimensional geological scanner, the laser echo tester and the electronic compass can also comprise manual qualitative description input data in other embodiments; after the data acquisition module finishes the acquisition of various data, the data information is sent to the data processing module.
The data processing module is used for classifying various data, and in the embodiment, the data can be divided into profile data, laser echo data and correction data.
The shape data is used for testing the integrity of the rock mass, and the volume node number J of the rock mass is subjected to point cloud data preprocessing, multi-view data splicing, equivalent surface dimensionality reduction and cluster partition identification on the acquired datavPerforming calculation, and then JvMatch KvThe value of (c).
The laser echo data are used for testing the hardness degree index of the rock, the echo intensity can be calculated through the distance of a measuring target acquired by the transmitted laser signal, and the uniaxial compressive strength of the rock mass can be calculated through the correlation between the echo intensity and the rock mass intensity.
The correction data comprises a groundwater influence correction factor K1Correction coefficient K for attitude influence of main structural plane2Initial stress state influence correction coefficient K3。
The data analysis module is composed of a neural network and is used for rapidly grading the surrounding rock through the analysis of the acquired and calculated data information; the neural network structure comprises: the device comprises an input layer, a hidden layer, an output layer, a normalization layer, a parameter optimization layer and an iteration layer; inputting a layer, representing coordinate values of the surrounding rock information; the hidden layer represents an algorithm from the surrounding rock information to an output result and comprises two n-dimensional matrixes; the output layer is used for controlling the output layer into a matrix of 1 x 5 through two n-dimensional matrixes of the hidden layer, and grading is carried out through the matrix; the output result normalization layer is used for increasing the accuracy of grading; the back propagation and parameter optimization layer is used for quantifying the quality of the output result normalization layer; and the iteration layer is used for improving the probability of outputting the result.
The output module can send the judgment result to a terminal or a cloud server, the terminal comprises a computer or a mobile phone and the like, and the cloud server can store each received data message; meanwhile, the terminal can also call data stored in the cloud server in real time for checking.
The method comprises the steps of determining rapid grading indexes of surrounding rocks; testing the integrity index of the rock mass; testing the rock hardness degree index; the correction indexes are determined, so that the surrounding rock can be accurately and quickly graded, and the judgment accuracy can be ensured through a neural network; meanwhile, different surrounding rocks can be rapidly and automatically graded through the grading system, the construction cost is effectively reduced, meanwhile, the working efficiency can be effectively improved through the full-automatic operation of the system, and the working period is shortened.
The invention is not limited to the foregoing embodiments. The invention extends to any novel feature or any novel combination of features disclosed in this specification and any novel method or process steps or any novel combination of features disclosed.
Claims (10)
1. A method for rapidly grading tunnel surrounding rocks is characterized by comprising the following steps: determining a rapid surrounding rock grading index; testing the integrity index of the rock mass; testing the rock hardness degree index; determining a correction index; rapidly judging the grade of the surrounding rock according to the index value based on the neural network; and outputting the judgment result.
2. The method for rapidly grading tunnel surrounding rocks according to claim 1, wherein the determined grading index is obtained by analyzing a common basic theory method for grading tunnel surrounding rocks; the common tunnel surrounding rock classification basic theory method comprises RMR, Q, RMi, GSI and BQ.
3. The method for rapidly grading tunnel surrounding rocks according to claim 1, wherein the method for testing the integrity index of the rock mass comprises the following steps: obtaining three-dimensional space point cloud data of target surrounding rock by adopting a three-dimensional geological scanning technology, calculating the joint number and the joint distance of the rock body, and further calculating to obtain the joint number J in each cubic meter of rock bodyvObtaining rock integrity index K according to standard recommendation tablev(ii) a Said JvIs calculated by
Wherein JvIs the volume adjustment number of rock mass, SiNumber of lines on 1m measuring line for group joint, S0Is 1m3The rock mass is not the number of the joints in groups.
4. The method for rapidly grading tunnel surrounding rocks according to claim 1, wherein the method for testing the rock hardness degree index comprises the following steps: calibrating the laser echo intensity of the surrounding rock and the uniaxial compressive strength of the rock mass into a functional relation, and estimating the compressive strength of the rock by using the scanned laser echo intensity of the rock mass;
the laser echo intensity calculation method comprises
Wherein E isiTransmitting signal intensity for the laser radar; etasysIs a system parameter; etaatmIs an atmospheric influence factor; drIs the lidar receiving aperture;
as a function of the dichroic reflectivity profile; thetaiIs the laser incident angle;
is the incident azimuth angle; thetasIs the laser exit angle;
is the backscatter azimuth; rdIs the distance between the target and the lidar system;
the function relation is Rc＝Ax+B，RcThe uniaxial compressive strength of the rock mass, x the laser echo strength of the surrounding rock, and A and B are coefficients.
5. The method for rapidly grading tunnel surrounding rocks according to claim 1, wherein the correction index includes a groundwater influence correction coefficient K1Correction coefficient K for attitude influence of main structural plane2Initial stress state influence correction coefficient K3；
The method for rapidly determining the groundwater influence correction coefficient comprises the following steps: observing the water outlet state of the tunnel face and the peripheral wall of the tunnel; selecting and determining the type of the water outlet state; water pressure test or water yield test; looking up a table to determine a correction coefficient;
the method for rapidly determining the attitude influence correction coefficient of the main structural surface comprises the following steps: measuring the inclination angle and the inclination of the main structural surface and the trend of the tunnel by using an electronic geological compass, identifying the included angle between the main structural surface and the trend of the tunnel and the inclination angle of the structural surface, sequentially solving the influence coefficient if a plurality of weak structural surfaces exist, and taking the maximum value;
the method for quickly determining the influence correction coefficient of the initial stress state comprises the following steps: lithological texture identification, wherein the lithological texture belongs to hard rock or soft rock; if the rock is hard rock, observing and recording the symbolic phenomenon of rock burst in the excavation process; if the rock is soft rock, observing and recording the marking phenomenon of core caking in the excavation process; recording the stripping and displacement of the cave wall rock mass and the development condition of a new crack in the excavation process; the table lookup determines the correction factor.
6. The method for rapidly grading tunnel surrounding rocks according to claim 1, wherein the method for rapidly judging the surrounding rock grade according to the index value based on the neural network comprises the following steps: dividing the surrounding rock information transmitted by each field actual measurement into three types of a, b and c, wherein a represents the uniaxial compressive strength R of the rock masscB represents the rock integrity index KvC represents the correction factor K1+K2+K3To obtain a data set of a, b, and c, which is used to construct the neural network.
7. The method for rapidly grading tunnel wall rocks according to claim 6, wherein the neural network structure comprises: inputting a layer, representing coordinate values of the surrounding rock information; the hidden layer represents an algorithm from the surrounding rock information to an output result and comprises two n-dimensional matrixes; the output layer is used for controlling the output layer into a matrix of 1 x 5 through two n-dimensional matrixes of the hidden layer, and grading is carried out through the matrix; the output result normalization layer is used for increasing the accuracy of grading; the back propagation and parameter optimization layer is used for quantifying the quality of the output result normalization layer; and the iteration layer is used for improving the probability of outputting the result.
8. A rapid grading system for tunnel surrounding rocks by applying the method of claim 1, which is characterized by comprising: the device comprises an acquisition module, a data processing module, a data analysis module and an output module; the acquisition module acquires data through hardware equipment; the data processing module comprises morphology data, laser echo data and correction data; the data analysis module analyzes by constructing a neural network; the output module comprises a terminal and a cloud server.
9. The system for rapidly grading tunnel surrounding rocks according to claim 8, wherein the hardware equipment of the acquisition module comprises: three-dimensional geological scanners, laser echo testers and electronic compasses.
10. The system of claim 8, wherein the neural network structure comprises: the device comprises an input layer, a hidden layer, an output layer, a normalization layer, a parameter optimization layer and an iteration layer.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110785371.5A CN113553763A (en) | 2021-07-12 | 2021-07-12 | Tunnel surrounding rock rapid grading method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110785371.5A CN113553763A (en) | 2021-07-12 | 2021-07-12 | Tunnel surrounding rock rapid grading method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113553763A true CN113553763A (en) | 2021-10-26 |
Family
ID=78102966
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110785371.5A Pending CN113553763A (en) | 2021-07-12 | 2021-07-12 | Tunnel surrounding rock rapid grading method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113553763A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114297824A (en) * | 2021-12-03 | 2022-04-08 | 山东科技大学 | Design method of deep high-stress hard rock plate cracking rock explosive energy release supporting system |
| CN115271366A (en) * | 2022-07-01 | 2022-11-01 | 中铁二十局集团有限公司 | Plateau tunnel surrounding rock classification model training method, device, equipment and medium |
| CN115271636A (en) * | 2022-07-01 | 2022-11-01 | 中铁二十局集团有限公司 | Plateau tunnel surrounding rock grading system |
| CN115271367A (en) * | 2022-07-01 | 2022-11-01 | 中铁二十局集团有限公司 | Plateau tunnel surrounding rock grading method, device, equipment and storage medium |
| CN115660420A (en) * | 2022-10-26 | 2023-01-31 | 中铁二院工程集团有限责任公司 | Grading method for bottom bulging deformation risk level of ballastless track railway tunnel |
| CN115930800A (en) * | 2023-02-21 | 2023-04-07 | 西南石油大学 | Tunnel face displacement field monitoring method based on three-dimensional laser point cloud |
| CN117292148A (en) * | 2023-11-27 | 2023-12-26 | 中交第二公路勘察设计研究院有限公司 | Tunnel surrounding rock level assessment method based on directional drilling and test data |
| CN117237403B (en) * | 2023-08-15 | 2024-03-29 | 天津大学 | Method and device for determining joint surface fitness of rock |
| CN117934484A (en) * | 2024-03-25 | 2024-04-26 | 中铁四局集团有限公司 | Tunnel face surrounding rock level judging method, equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20060058168A (en) * | 2004-11-24 | 2006-05-29 | 손호웅 | Remote roughness measurement method for discontinuities of rock mass by laser scanning and system of the same |
| CN105842168A (en) * | 2016-03-17 | 2016-08-10 | 河海大学 | Surrounding rock grading method based on laser scanning technique |
| CN110795793A (en) * | 2019-11-27 | 2020-02-14 | 中铁西南科学研究院有限公司 | Tunnel surrounding rock rapid grading equipment system and operation method thereof |
| CN110852908A (en) * | 2019-05-31 | 2020-02-28 | 西南交通大学 | Surrounding rock grading method |
| CN112529330A (en) * | 2020-12-24 | 2021-03-19 | 东南大学 | Tunnel surrounding rock geological grading information prediction method based on Bayesian neural network |
-
2021
- 2021-07-12 CN CN202110785371.5A patent/CN113553763A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20060058168A (en) * | 2004-11-24 | 2006-05-29 | 손호웅 | Remote roughness measurement method for discontinuities of rock mass by laser scanning and system of the same |
| CN105842168A (en) * | 2016-03-17 | 2016-08-10 | 河海大学 | Surrounding rock grading method based on laser scanning technique |
| CN110852908A (en) * | 2019-05-31 | 2020-02-28 | 西南交通大学 | Surrounding rock grading method |
| CN110795793A (en) * | 2019-11-27 | 2020-02-14 | 中铁西南科学研究院有限公司 | Tunnel surrounding rock rapid grading equipment system and operation method thereof |
| CN112529330A (en) * | 2020-12-24 | 2021-03-19 | 东南大学 | Tunnel surrounding rock geological grading information prediction method based on Bayesian neural network |
Non-Patent Citations (4)
| Title |
|---|
| 吴青华等: "三维激光扫描数据处理技术及其工程应用", vol. 1, 30 November 2020, 山东大学出版社, pages: 188 - 190 * |
| 李林: "岩土工程", vol. 1, 31 March 2021, 武汉理工大学出版社, pages: 16 * |
| 杜松等: "激光雷达回波强度数据辐射特性分析", 中国科学院大学学报, vol. 36, no. 3, pages 392 - 400 * |
| 韩贤权: "地面Lidar测量及其在岩体结构面提取中的应用", vol. 1, 31 January 2019, 中国地质大学出版社, pages: 19 * |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114297824A (en) * | 2021-12-03 | 2022-04-08 | 山东科技大学 | Design method of deep high-stress hard rock plate cracking rock explosive energy release supporting system |
| CN115271366A (en) * | 2022-07-01 | 2022-11-01 | 中铁二十局集团有限公司 | Plateau tunnel surrounding rock classification model training method, device, equipment and medium |
| CN115271636A (en) * | 2022-07-01 | 2022-11-01 | 中铁二十局集团有限公司 | Plateau tunnel surrounding rock grading system |
| CN115271367A (en) * | 2022-07-01 | 2022-11-01 | 中铁二十局集团有限公司 | Plateau tunnel surrounding rock grading method, device, equipment and storage medium |
| CN115660420A (en) * | 2022-10-26 | 2023-01-31 | 中铁二院工程集团有限责任公司 | Grading method for bottom bulging deformation risk level of ballastless track railway tunnel |
| CN115660420B (en) * | 2022-10-26 | 2024-01-23 | 中铁二院工程集团有限责任公司 | Grading method for bottom bulge deformation risk level of ballastless track railway tunnel |
| CN115930800A (en) * | 2023-02-21 | 2023-04-07 | 西南石油大学 | Tunnel face displacement field monitoring method based on three-dimensional laser point cloud |
| CN115930800B (en) * | 2023-02-21 | 2023-05-05 | 西南石油大学 | Tunnel face displacement field monitoring method based on three-dimensional laser point cloud |
| CN117237403B (en) * | 2023-08-15 | 2024-03-29 | 天津大学 | Method and device for determining joint surface fitness of rock |
| CN117292148A (en) * | 2023-11-27 | 2023-12-26 | 中交第二公路勘察设计研究院有限公司 | Tunnel surrounding rock level assessment method based on directional drilling and test data |
| CN117292148B (en) * | 2023-11-27 | 2024-02-09 | 中交第二公路勘察设计研究院有限公司 | Tunnel surrounding rock level assessment method based on directional drilling and test data |
| CN117934484A (en) * | 2024-03-25 | 2024-04-26 | 中铁四局集团有限公司 | Tunnel face surrounding rock level judging method, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113553763A (en) | Tunnel surrounding rock rapid grading method and system | |
| CN103114848A (en) | Formation fracture space reconstruction method based on rock core measure | |
| CN104749624A (en) | Method for synchronously realizing seismic lithofacies identification and quantitative assessment of uncertainty of seismic lithofacies identification | |
| CN113869629A (en) | Laser point cloud-based power transmission line safety risk analysis, judgment and evaluation method | |
| CN113360587B (en) | Land surveying and mapping equipment and method based on GIS technology | |
| Corradetti et al. | Quantitative analysis of folds by means of orthorectified photogrammetric 3D models: a case study from Mt. Catria, Northern Apennines, Italy | |
| CN108830317B (en) | Rapid and fine evaluation method for joint attitude of surface mine slope rock mass based on digital photogrammetry | |
| CN115131486B (en) | Engineering exploration data acquisition system and method | |
| Laux et al. | Terrestrial laser scanning and fracture network characterisation–perspectives for a (semi-) automatic analysis of point cloud data from outcrops | |
| CN110135515B (en) | Automatic partitioning method for homogeneous region of rock mass structure based on image texture | |
| CN104316961A (en) | Method for obtaining geological parameters of weathered layer | |
| CN112464513A (en) | RQD based on photogrammetry and RQD inversiontOptimal threshold t solving method | |
| CN112200417A (en) | Based on photogrammetry, BQ,RQDtImproved Mathews stability chart evaluation method for ground stress | |
| CN113568041B (en) | Repeatability analysis method and system for time-lapse seismic three-dimensional towing cable acquired data | |
| CN110806444B (en) | Seabed sediment recognition and classification method based on shallow stratum profiler and SVM | |
| CN110702632B (en) | Three-dimensional modeling method for hyperspectral information of deep rock and ore | |
| CN111127630B (en) | Random modeling method for hyperspectral alteration information of drill core in three-dimensional space | |
| CN112132403A (en) | RQD based on photogrammetry and BQ inversiontOptimal threshold t solving method | |
| CN114092596A (en) | Rapid and automatic solving and drawing method for rock RQDt | |
| Liu et al. | A novel system for multivariate analysis of discontinuities in fractured rock masses based on manifold learning and fractal models | |
| Ahlgren et al. | Using 3-D outcrop laserscan for fracture analysis | |
| Tesfamariam | Comparing discountinuity surface roughness derived from 3D terrestrial laser scan data with traditional Field-based methods | |
| Donovan et al. | The application of three-dimensional imaging to rock discontinuity characterization | |
| Wang et al. | Modeling of the Three-Dimensional Point Cloud Based on the Binocular Stereovision and Structure Identification | |
| Chen et al. | A human-machine interaction method for rock discontinuities mapping by three-dimensional point clouds with noises |
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 |