CN110414064B - Construction method of structural surface morphology and shear strength correlation model - Google Patents

Construction method of structural surface morphology and shear strength correlation model Download PDF

Info

Publication number
CN110414064B
CN110414064B CN201910582779.5A CN201910582779A CN110414064B CN 110414064 B CN110414064 B CN 110414064B CN 201910582779 A CN201910582779 A CN 201910582779A CN 110414064 B CN110414064 B CN 110414064B
Authority
CN
China
Prior art keywords
structural surface
shearing
height
shear strength
structural
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201910582779.5A
Other languages
Chinese (zh)
Other versions
CN110414064A (en
Inventor
黄曼
罗战友
杜时贵
马成荣
陈洁
邹宝平
洪陈杰
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
University of Shaoxing
Original Assignee
University of Shaoxing
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by University of Shaoxing filed Critical University of Shaoxing
Priority to CN201910582779.5A priority Critical patent/CN110414064B/en
Publication of CN110414064A publication Critical patent/CN110414064A/en
Application granted granted Critical
Publication of CN110414064B publication Critical patent/CN110414064B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • 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
    • G01N3/24—Investigating strength properties of solid materials by application of mechanical stress by applying steady shearing forces
    • 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
    • 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
    • G01N2203/02—Details not specific for a particular testing method
    • G01N2203/0202—Control of the test
    • G01N2203/0212—Theories, calculations
    • G01N2203/0218—Calculations based on experimental data
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
    • Y02T90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Physics & Mathematics (AREA)
  • Computing Systems (AREA)
  • Software Systems (AREA)
  • Evolutionary Computation (AREA)
  • Computational Linguistics (AREA)
  • Molecular Biology (AREA)
  • Biophysics (AREA)
  • General Engineering & Computer Science (AREA)
  • Biomedical Technology (AREA)
  • Mathematical Physics (AREA)
  • Data Mining & Analysis (AREA)
  • Artificial Intelligence (AREA)
  • Chemical & Material Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Biochemistry (AREA)
  • Immunology (AREA)
  • Pathology (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Investigating Strength Of Materials By Application Of Mechanical Stress (AREA)

Abstract

A construction method of a structural surface morphology and shear strength correlation model comprises the following steps: (1) Extracting point cloud data of the initial form of the model structural surface by using a three-dimensional laser scanner, and selecting the structural surface to perform a structural surface shearing test until the structural surface is destroyed and stops; (2) Processing the point cloud data and the picture shot by the high-speed camera to obtain the structural surface fluctuation form of the key points in each shearing process, and obtaining various geometric parameter characteristic information of the surface of the structural surface; (3) In the m shearing processes, a data set and a shearing strength data vector are constructed through analysis and screening; (4) Inputting the constructed data set into a deep neural network, taking the shearing strength data vector as an output result, and obtaining a required model through training of the deep neural network; (5) And (4) obtaining the optimal functional relation between the key parameter factors and the peaks and between the key parameter factors and the intensities according to the network training model in the step (4). The invention can accurately estimate the shear strength of the structural surface.

Description

Construction method of structural surface morphology and shear strength correlation model
Technical Field
The invention relates to a statistical model of data mining and structural surface morphology parameters and shear strength, in particular to a construction method of a correlation model considering the structural surface morphology parameters and the shear strength based on the data mining, which is suitable for occasions for estimating the structural surface shear strength according to the structural surface morphology parameters.
Background
The structural surface roughness characterization method comprises a JRC method, a fractal geometry description method, a statistical parameter characterization method, a comprehensive parameter characterization method and the like. In quantifying structural surface roughness using fractal dimension, results are rich, turk and peaceThe results of the study are representative of the early days. For statistical parameters, the related characterization parameters are more, and mainly include mean slope root-mean-square Z 2 Structure function SF, etc. And structural surface roughness parameters JRCv and SRv characterized by the variation function, and the like. The determination of the surface roughness of the structural surface is directly influenced by the extraction precision of the surface coordinate data of the structural surface, and the uncertainty of the geometric morphology cannot be accurately expressed by counting the average value of the roughness coefficient of the structural surface by the traditional structural surface morphology statistical method, so that partial information of the surface morphology is lost. The destructive characteristic of the surface morphology of the structural surface in the shearing process determines the peak shear strength, while the current direct shear test can only obtain the final surface destructive morphology of the structural surface.
With the coming of the big data era, the data mining method is used in the research direction of geotechnical engineering, and the GSA-BP neural network model for the Wangcheng is used for predicting displacement according to the monitored surrounding rock deformation data in the actual engineering; and applying the trained BP neural network to actual engineering to analyze mechanical parameters of tunnel surrounding rocks in Zhou Jianchun and the like. The data mining is widely applied to nonlinear function approximation, time sequence analysis, data classification, mode recognition, information processing, image processing and the like in the process of searching information hidden in a large amount of engineering data through an algorithm, and provides a new idea for researching the shear strength of a rock structural surface.
The analysis shows that the influence and contribution degree of the structural surface morphology geometric parameters on the shearing strength can be analyzed only by acquiring the high-precision structural surface morphology and the three-dimensional morphology change rule in the shearing process from the basic composition of the structural surface morphology.
Disclosure of Invention
In order to overcome the defects that the average value of the roughness coefficient of the traditional structural surface morphology statistics structural surface cannot accurately express the uncertainty of the geometric morphology and part of information of the structural surface morphology is lost, the invention provides a method for establishing a correlation model of the structural surface geometric morphology characteristics and the structural surface peak shear strength by a data mining method, which can better describe the influence of the structural surface morphology on the peak shear strength, thereby accurately estimating the structural surface shear strength.
The technical scheme adopted by the invention for solving the technical problems is as follows:
a construction method of a structural surface topography and shear strength correlation model comprises the following steps:
(1) Using a three-dimensional laser scanner to extract point cloud data of the initial form of the model structural surface, and selecting the structural surface to perform a structural surface shearing test until the structural surface is damaged and stops; in the shearing process, a high-speed camera is used for shooting a morphological picture of the whole shearing process of the structural plane;
(2) The point cloud data and the picture shot by the high-speed camera are processed by MATLAB software to obtain the structural surface fluctuation form of the key points in each shearing process, and various geometric parameter characteristic information of the structural surface is obtained, including: first derivative of plateau height, i.e. slope z 2 Roughness index R p A climbing angle I and an average inclination angle I A Maximum effective tilt angle
Figure GDA0002193599990000021
Maximum possible contact area ratio A 0 A roughness parameter C, a structural function SF, a root mean square RMS of protrusion height, a mean value CLA of protrusion height, a mean square value MSV of the ratio of positive and negative protrusion height difference to the length of the middle line, an autocorrelation function and a spectral density function;
(3) Respectively recording the i-th peak shear strength tau in the m shearing processes i And structural surface geometric shape parameters in the shearing process and other parameters A related to influence shearing i I is less than or equal to m, and after m times of tests are finished, a data set A is constructed through analysis and screening = [ A = 1 ，A 2 ，...，A m ]And shear strength data vector τ = [ τ ] 1 ，τ 2 ，τ 3 ，...，τ m ]；
(4) Inputting the constructed data set into a deep neural network, taking the shearing strength data vector as an output result, and obtaining a required model through training of the deep neural network;
(5) And obtaining the optimal functional relation between key parameter factors and peaks and between intensities according to the network training model for obtaining the geometric shape parameters and the peak shear strength.
Further, in the step (4), the process is as follows:
4.1 Defining a network architecture, initializing parameters of the neural network of m layers, initializing a weight W by adopting a random method, initializing a bias b to be 0, and matching dimensionality between each layer;
4.2 Executing a forward propagation module, executing a forward propagation linear part, executing a forward propagation activation part, and executing overall m-layer forward propagation, wherein m-1 forward propagation using relu as an activation function is required, and then the forward propagation using sigmoid as the activation function is followed;
4.3 Computing a loss function, computing an objective function using cross entropy;
4.4 Execute a back propagation module, the back propagation being used to calculate a gradient of the loss function with respect to the parameter, the back propagation calculation being similar to the forward propagation;
4.5 Updating parameters by applying a gradient descent method;
4.6 The imported data is trained by a deep neural network, and the required model is obtained after multiple times of training.
The invention has the following beneficial effects: 1) The method can obtain the contribution degree of the geometric shape parameters of the rock structural surface to the peak value shearing strength value in the shearing process; 2) The method is helpful for revealing the mechanical mechanism of rock structural plane damage; 3) The method can obtain the optimal relation function of the geometric shape parameters of the structural surface and the peak shear strength.
Drawings
Fig. 1 is a schematic diagram of an association model establishment process.
Fig. 2 is a schematic diagram corresponding to the key points.
Detailed Description
The invention is further described below with reference to the accompanying drawings.
Referring to fig. 1 and 2, a method for constructing a correlation model between surface topography parameters and shear strength of a structural surface comprises the following steps:
selecting model structural surface to carry out
(1) Extracting point cloud data of the initial form of the model structural surface by using a three-dimensional laser scanner, and selecting the structural surface to perform a structural surface shearing test until the structural surface is destroyed and stops; in the shearing process, a high-speed camera is used for shooting a morphological picture of the whole shearing process of the structural plane;
(2) The point cloud data and the pictures shot by the high-speed camera are processed by software such as MATLAB (matrix laboratory) and the like to obtain t in each shearing process 1 、t 2 、t 3 、t 4 The method is characterized in that the fluctuation form of the structural surface at any moment is used for obtaining various geometric parameter characteristic information in all directions of the surface of the structural surface, and the method comprises the following steps: first derivative of plateau height, i.e. slope z 2 Roughness index R p A climbing angle I and an average inclination angle I A Maximum effective tilt angle
Figure GDA0002193599990000041
Maximum possible contact area ratio A 0 A roughness parameter C, a structure function SF, a root mean square RMS of protrusion height, a mean value CLA of protrusion height, a mean square value MSV of a ratio of positive and negative protrusion height difference to a median length, an autocorrelation function, a spectral density function, etc., wherein
Figure GDA0002193599990000042
Wherein M is the total amount of the whole hatching line, y i The height of the projection of the ith measuring point is delta, and the delta is a sampling interval;
Figure GDA0002193599990000043
in the formula, x i Is the abscissa, y, of the ith measuring point i The height of the projection of the ith measuring point is L, and the joint trace length is L. For an ideal smooth joint, R p ＝1；
Figure GDA0002193599990000044
In the formula, y i Is the ith oneThe height of the projection of the measuring point is L, and the joint trace length is L;
Figure GDA0002193599990000045
in the formula, A f Is the sum of the areas of the elements facing the shearing direction, A t The actual area of the rough structural surface;
Figure GDA0002193599990000052
in the formula, A 0 In order to maximize the possible contact area ratio,
Figure GDA0002193599990000053
the roughness parameter C is a dimensionless roughness parameter which is the maximum effective inclination angle and is calculated by the fitting test value of the formula;
Figure GDA0002193599990000054
wherein M is the total amount of the whole hatching line, y i The height of the projection of the ith measuring point is shown, and dx is the sampling length;
Figure GDA0002193599990000055
wherein M is the total amount of the whole hatching line, y i The height of the projection of the ith measuring point is shown, and dx is the sampling length;
Figure GDA0002193599990000056
wherein M is the total amount of the whole hatching line, y i The height of the projection of the ith measuring point is shown, and dx is the sampling length;
Figure GDA0002193599990000057
wherein M is the total amount of the whole hatching line, y i The height of the protrusion at the ith measurement point is dx, which is the sampling length. Table 1 shows the initial geometric parameter values obtained from ten standard profile curves of Barton.
Figure GDA0002193599990000051
TABLE 1 (3) in the m shearing processes, the i-th peak shear strength τ is recorded i And structural surface geometric shape parameters in the cutting process and other parameters A related to the influence on the cutting i I is less than or equal to m, and after m times of tests are finished, a neural network test data set A = [ A ] is constructed through analysis and screening 1 ，A 2 ，...，A m ]With shear strength vector τ = [ τ ] 1 ，τ 2 ，τ 3 ...τ m ]；
(4) Inputting the constructed data set into a deep neural network, taking the shearing strength data vector as an output result, and obtaining a required model through training of the deep neural network; the process is as follows:
4.1 Defining a network architecture, initializing parameters of the neural network of m layers, initializing weight W by adopting a random method, initializing bias b to be 0, and matching dimensionalities between every two layers;
4.2 Executing a forward propagation module, executing a forward propagation linear part, executing a forward propagation activation part, and executing overall m-layer forward propagation, wherein m-1 forward propagation using relu as an activation function is required, and then the forward propagation using sigmoid as the activation function is followed;
4.3 Computing a loss function, computing an objective function using cross entropy;
4.4 Execute a back propagation module, the back propagation being used to calculate a gradient of the loss function with respect to the parameter, the back propagation calculation being similar to the forward propagation;
4.5 Updating parameters by applying a gradient descent method;
4.6 The imported data is trained by a deep neural network, and the required model is obtained after multiple times of training.
(5) And obtaining a shearing model of the geometric morphology parameters and the peak shearing strength according to the obtained structural surface geometric morphology parameters and the data mining processing result, and obtaining the optimal functional relation between key parameter factors and peaks and between the key parameter factors and the peak shearing strength.
The embodiments described in this specification are merely illustrative of implementations of the inventive concepts, which are intended for purposes of illustration only. The scope of the present invention should not be construed as being limited to the particular forms set forth in the examples, but rather as being defined by the claims and the equivalents thereof which can occur to those skilled in the art upon consideration of the present inventive concept.

Claims (3)

1. A method for constructing a structural surface morphology and shear strength correlation model is characterized by comprising the following steps:
(1) Using a three-dimensional laser scanner to extract point cloud data of the initial form of the model structural surface, and selecting the structural surface to perform a structural surface shearing test until the structural surface is damaged and stops; in the shearing process, a high-speed camera is used for shooting a morphological picture of the whole shearing process of the structural plane;
(2) The point cloud data and the picture shot by the high-speed camera are processed by MATLAB software to obtain the structural surface fluctuation form of the key points in each shearing process, and various geometric parameter characteristic information of the structural surface is obtained, including: first derivative of plateau height, i.e. slope z 2 Roughness index R p A climbing angle I and an average inclination angle I A Maximum effective tilt angle
Figure FDA0003933942350000011
Maximum possible contact area ratio A 0 A roughness parameter C, a structural function SF, a root mean square RMS of protrusion height, a mean value CLA of protrusion height, a mean square value MSV of the ratio of positive and negative protrusion height difference to the length of the middle line, an autocorrelation function and a spectral density function;
(3) Respectively recording the i-th peak shear resistance in the m shearing processesIntensity τ i And structural surface geometric shape parameters in the shearing process and other parameters A related to influence shearing i I is less than or equal to m, and after m times of tests are finished, a data set A is constructed through analysis and screening = [ A = 1 ，A 2 ，...，A m ]And shear strength data vector τ = [ τ ] 1 ，τ 2 ，τ 3 ，...，τ m ]；
(4) Inputting the constructed data set into a deep neural network, taking the shearing strength data vector as an output result, and obtaining a required model through training of the deep neural network;
(5) And obtaining the optimal functional relation between key parameter factors and peaks and between intensities according to the network training model for obtaining the geometric shape parameters and the peak shear strength.
2. The method for constructing the correlation model between the surface morphology of the structural plane and the shear strength as claimed in claim 1, wherein in the step (4), the process is as follows:
4.1 Defining a network architecture, initializing parameters of the neural network of m layers, initializing a weight W by adopting a random method, initializing a bias b to be 0, and matching dimensionality between each layer;
4.2 Executing a forward propagation module, executing a forward propagation linear part, executing a forward propagation activation part, and executing overall m-layer forward propagation, wherein m-1 forward propagation using relu as an activation function is required, and then the forward propagation using sigmoid as the activation function is followed;
4.3 Computing a loss function, computing an objective function using cross entropy;
4.4 Execute a back propagation module, the back propagation being used to calculate a gradient of the loss function with respect to the parameter, the back propagation calculation being similar to the forward propagation;
4.5 Updating parameters by applying a gradient descent method;
4.6 The imported data is trained by a deep neural network, and the required model is obtained after multiple times of training.
3. The method for constructing the structural surface topography-shear strength correlation model according to claim 1 or 2, wherein in the step (2),
Figure FDA0003933942350000021
wherein M is the total amount of the whole hatching line, y i The height of the projection of the ith measuring point is delta, and the delta is a sampling interval;
Figure FDA0003933942350000022
in the formula, x i Is the abscissa, y, of the ith measuring point i Is the height of the projection at the ith test point, L is the joint length, and for an ideal smooth joint, R p ＝1；
Figure FDA0003933942350000023
In the formula, y i The height of the projection of the ith measuring point is L, and the length of the joint trace is L;
Figure FDA0003933942350000024
in the formula, A f Is the sum of the areas of the elements facing the shearing direction, A t The actual area of the rough structural surface;
Figure FDA0003933942350000025
in the formula, A 0 In order to maximize the possible contact area ratio,
Figure FDA0003933942350000026
at the maximum effective angle of inclination, coarseThe roughness parameter C is a dimensionless roughness parameter and is calculated by fitting a test value according to the formula;
Figure FDA0003933942350000027
wherein M is the total amount of the whole hatching line, y i The height of the projection of the ith measuring point is shown, and dx is the sampling length;
Figure FDA0003933942350000031
wherein M is the total amount of the whole hatching line, y i The height of the projection of the ith measuring point is adopted, and dx is the sampling length;
Figure FDA0003933942350000032
wherein M is the total amount of the whole hatching line, y i The height of the projection of the ith measuring point is shown, and dx is the sampling length;
Figure FDA0003933942350000033
wherein M is the total amount of the whole hatching line, y i The height of the protrusion at the ith measurement point is dx, which is the sampling length.
CN201910582779.5A 2019-07-01 2019-07-01 Construction method of structural surface morphology and shear strength correlation model Active CN110414064B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910582779.5A CN110414064B (en) 2019-07-01 2019-07-01 Construction method of structural surface morphology and shear strength correlation model

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910582779.5A CN110414064B (en) 2019-07-01 2019-07-01 Construction method of structural surface morphology and shear strength correlation model

Publications (2)

Publication Number Publication Date
CN110414064A CN110414064A (en) 2019-11-05
CN110414064B true CN110414064B (en) 2023-03-24

Family

ID=68358655

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910582779.5A Active CN110414064B (en) 2019-07-01 2019-07-01 Construction method of structural surface morphology and shear strength correlation model

Country Status (1)

Country Link
CN (1) CN110414064B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111366475B (en) * 2020-03-25 2023-02-03 中国电建集团成都勘测设计研究院有限公司 Method for acquiring shear strength parameters of particle-type structural surface and structural belt
CN113049403B (en) * 2021-03-02 2022-11-29 宁波大学 Structural plane normal unloading shear damage test method considering morphology frequency spectrum characteristics

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2015180397A1 (en) * 2014-05-31 2015-12-03 华为技术有限公司 Method and device for recognizing data category based on deep neural network
CN105466790A (en) * 2015-11-10 2016-04-06 内蒙古科技大学 Evaluation method of shear strength of rock structural surface with anisotropic characteristics
CN109269914A (en) * 2018-10-11 2019-01-25 山东科技大学 A kind of analysis method and pilot system of study of rocks joint plane failure by shear process

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2015180397A1 (en) * 2014-05-31 2015-12-03 华为技术有限公司 Method and device for recognizing data category based on deep neural network
CN105466790A (en) * 2015-11-10 2016-04-06 内蒙古科技大学 Evaluation method of shear strength of rock structural surface with anisotropic characteristics
CN109269914A (en) * 2018-10-11 2019-01-25 山东科技大学 A kind of analysis method and pilot system of study of rocks joint plane failure by shear process

Also Published As

Publication number Publication date
CN110414064A (en) 2019-11-05

Similar Documents

Publication Publication Date Title
CN103926156B (en) A kind of three-dimensional rock structural face shears mechanical behavior multifractal appraisal procedure
CN108489402B (en) Rapid and fine dereferencing method for surface mine slope rock mass joint scale based on three-dimensional laser scanning
CN105466790B (en) A kind of rock structural face shear strength appraisal procedure of anisotropic character
CN110414064B (en) Construction method of structural surface morphology and shear strength correlation model
CN114091606B (en) Tunnel blasting blast hole half-eye mark identification and damage flatness evaluation classification method
CN111985552B (en) Method for detecting diseases of thin strip-shaped structure of airport pavement under complex background
CN108445188A (en) The following slope stability expression of harshness coefficient size effect of rock structural face based on middle intelligence interval function
CN109931876A (en) A method of passing through photogrammetric geotechnical sample deformation
CN112329939A (en) Non-sampling point rock-soil parameter evaluation method based on random forest machine learning algorithm
CN109598015B (en) Grading evaluation method for rock mass fragmentation degree of fragmentation structure
CN115984850A (en) Lightweight remote sensing image semantic segmentation method based on improved Deeplabv3+
CN109085643A (en) The early substep joint inversion method to wave
Catalucci et al. Comparison between point cloud processing techniques
CN110363299A (en) Space reasoning by cases method towards delamination-terrane of appearing
CN105373814B (en) A kind of true broad leaf tree organ classes recognition methods based on laser point cloud data
Peng et al. Automatic 3D image based finite element modelling for metallic foams and accuracy verification of digital volume correlation
CN108460422B (en) Submarine geomorphy kind identification method based on depth distribution feature
CN116245872A (en) Aircraft structure crack detection method based on convolutional neural network
CN115791803A (en) Deep-buried tunnel surrounding rock blasting damage test system and test method
CN115661071A (en) Composite material processing surface defect detection and evaluation method based on deep learning
Wang et al. Identification of rocky ledge on steep, high slopes based on UAV photogrammetry
KR102070651B1 (en) Estimation method of joint roughness coefficient using image data
Nikkhah et al. Application of pattern recognition analysis of rock acoustic emission for determination of Kaiser Effect
Kibitkin et al. Formation of a single image of material surfaces to measure displacement and strain fields
CN112577450B (en) Engineering rock mass structural surface roughness coefficient determination method based on multiple regression analysis

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