CN115753643A - Rock mass fracture intelligent identification method and system integrating three-dimensional scanning and image spectrum - Google Patents
Rock mass fracture intelligent identification method and system integrating three-dimensional scanning and image spectrum Download PDFInfo
- Publication number
- CN115753643A CN115753643A CN202211291423.4A CN202211291423A CN115753643A CN 115753643 A CN115753643 A CN 115753643A CN 202211291423 A CN202211291423 A CN 202211291423A CN 115753643 A CN115753643 A CN 115753643A
- Authority
- CN
- China
- Prior art keywords
- fracture
- dimensional
- rock mass
- image
- point cloud
- 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 93
- 238000001228 spectrum Methods 0.000 title claims abstract description 56
- 238000000034 method Methods 0.000 title claims abstract description 52
- 229910052500 inorganic mineral Inorganic materials 0.000 claims abstract description 66
- 239000011707 mineral Substances 0.000 claims abstract description 66
- 230000003595 spectral effect Effects 0.000 claims abstract description 66
- 238000012545 processing Methods 0.000 claims abstract description 27
- 238000003062 neural network model Methods 0.000 claims description 18
- 230000008569 process Effects 0.000 claims description 17
- 238000012549 training Methods 0.000 claims description 11
- 230000009466 transformation Effects 0.000 claims description 9
- 238000003384 imaging method Methods 0.000 claims description 8
- 238000012360 testing method Methods 0.000 claims description 7
- 230000004927 fusion Effects 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 4
- 238000004611 spectroscopical analysis Methods 0.000 claims 6
- 238000000605 extraction Methods 0.000 abstract description 9
- 230000007547 defect Effects 0.000 abstract description 2
- 206010017076 Fracture Diseases 0.000 description 172
- 208000010392 Bone Fractures Diseases 0.000 description 161
- 238000005516 engineering process Methods 0.000 description 11
- 239000000945 filler Substances 0.000 description 7
- 238000012937 correction Methods 0.000 description 5
- 238000001914 filtration Methods 0.000 description 5
- 239000013589 supplement Substances 0.000 description 5
- 238000013507 mapping Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 3
- 238000013480 data collection Methods 0.000 description 3
- 239000000463 material Substances 0.000 description 3
- 230000000007 visual effect Effects 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000008030 elimination Effects 0.000 description 2
- 238000003379 elimination reaction Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 235000019738 Limestone Nutrition 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 229910052736 halogen Inorganic materials 0.000 description 1
- 150000002367 halogens Chemical class 0.000 description 1
- 238000011065 in-situ storage Methods 0.000 description 1
- 239000006028 limestone Substances 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000013508 migration Methods 0.000 description 1
- 230000005012 migration Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000001502 supplementing effect Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/30—Assessment of water resources
Landscapes
- Length Measuring Devices With Unspecified Measuring Means (AREA)
Abstract
The invention discloses a rock mass fracture intelligent identification system and method integrating three-dimensional scanning and image spectrum, which comprises the following steps: acquiring three-dimensional point cloud data of a target rock mass through three-dimensional scanning; processing the three-dimensional point cloud data to obtain a fracture point cloud data set under a two-dimensional coordinate system; acquiring image information and spectral information of a target rock mass through spectral scanning; extracting mineral distribution characteristics based on spectral information, and extracting fracture image characteristics based on image information; based on the mineral distribution characteristics and the fracture image characteristics, utilizing a filling fracture boundary intelligent identification model to obtain boundary coordinates of a filling fracture and filling mineral information; and checking and merging the boundary coordinates of the filled fracture and the fracture point cloud data set under the two-dimensional coordinate system, so as to realize comprehensive and accurate identification of the rock mass fracture. The method can effectively make up for the defects that accurate identification and efficient parameter extraction cannot be realized on the filled fracture by three-dimensional laser scanning, and greatly improves the fracture identification accuracy.
Description
Technical Field
The invention relates to the technical field of rock mass fracture identification, in particular to a rock mass fracture intelligent identification method and system integrating three-dimensional scanning and image spectrum.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
The rock mass has a large number of fracture structures, and the structures have great influence on the physical and mechanical performance indexes, deformation characteristics, seepage properties and long-term stability of the rock mass. The fractures can be divided into filling fractures and non-filling fractures according to whether the fractures are filled, common fracture fillers comprise gravels, sandy soil, limestone and the like formed by tectonic action, weathering action and underground water action, the fracture fillers have high component discrimination with surrounding rocks, and the component consistency probability is low.
In the field of longitudinal rock fracture identification, common identification methods at present include a visual observation method, an image identification method, a three-dimensional laser scanning method and the like. The visual observation method usually depends too much on manual experience, has high requirement on professional skill and knowledge reserve of an observer, cannot realize accurate quantitative analysis on the fracture, is easily limited by environmental factors such as weather, light and the like, and has the advantages of large workload, low efficiency, high labor cost and low economic benefit; the image recognition method is often limited by image quality, the requirements on algorithm and model integrity are high, training data often need to be preprocessed, original model parameters cannot be directly utilized, and finally the recognition precision needs to be improved; the three-dimensional laser scanning technology directly carries out three-dimensional sampling on the surface of a rock body through three-dimensional laser scanning equipment, compared with the traditional technology, although the rock body fracture can be identified quickly, in situ and with high precision, the three-dimensional scanning can only carry out data sampling on the surface of the rock body, the fracture internal space of the filled fracture is filled with minerals and the like, and the fracture boundary obtained through scanning is easy to distort and even misjudge and the like. In summary, the fracture identification using only one technology has a certain limitation in identification accuracy.
Disclosure of Invention
In order to solve the problems, the invention provides a rock mass fracture intelligent identification method and system integrating three-dimensional scanning and image spectra, which realize accurate identification of non-filled fractures and fuzzy identification of filled fractures by using a three-dimensional scanning technology, realize accurate identification of filled fractures by using the image spectra technology and a neural network, supplement and check a three-dimensional scanning result, and finally realize accurate, comprehensive, rapid and intelligent identification of rock mass fractures.
In some embodiments, the following technical scheme is adopted:
a rock mass fracture intelligent identification method integrating three-dimensional scanning and image spectra comprises the following steps:
acquiring three-dimensional point cloud data of a target rock mass through three-dimensional scanning;
processing the three-dimensional point cloud data, extracting a discontinuous point set coordinate, and performing dimension transformation on the extracted discontinuous point set coordinate to obtain a fracture point cloud data set under a two-dimensional coordinate system;
acquiring image information and spectral information of a target rock mass through spectral scanning;
extracting mineral distribution characteristics based on spectral information, and extracting fracture image characteristics based on image information; based on the mineral distribution characteristics and the fracture image characteristics, utilizing a filling fracture boundary intelligent identification model to obtain boundary coordinates of a filling fracture and filling mineral information;
and checking and merging the boundary coordinates of the filled fracture and the fracture point cloud data set under the two-dimensional coordinate system, so as to realize comprehensive and accurate identification of the rock mass fracture.
As a further scheme, dimension transformation is performed on the extracted coordinates of the discontinuous point set, and the specific process is as follows: and manually deleting the data in the z direction of the three-dimensional (x, y, z) coordinates of the extracted discontinuous point set, and converting the data into a fracture point cloud data set in a two-dimensional coordinate system.
As a further scheme, the mineral distribution characteristics are extracted based on spectral information, and the specific process is as follows:
acquiring a spectral curve of each pixel point in an image, determining whether the two pixel points belong to the same rock mass based on whether the spectral angles of two adjacent spectral curves are smaller than a set threshold, matching the spectral curves with a spectral database, and determining the specific mineral type corresponding to the spectral curves; thus determining the mineral type and mineral distribution condition corresponding to each pixel point, and performing mineral map filling; wherein, a spectrum curve and a mineral molecular formula matched with the spectrum curve are prestored in the spectrum database.
As a further scheme, based on the mineral distribution characteristics and the fracture image characteristics, a filling fracture boundary intelligent identification model is used to obtain boundary coordinates of a filling fracture and filling mineral information, and the specific process is as follows: inputting fracture image characteristics and mineral distribution characteristics obtained by processing the imaging spectrum image cube, matching fracture coordinates of the same position of a target rock body with a mineral mapping area, extracting the boundary of the overlapped area of the two areas, regarding the boundary as a filling fracture area, and finally realizing the output of the filling fracture boundary coordinates and mineral components by combining with the mineral mapping.
As a further scheme, the intelligent recognition model for the filling fracture boundary adopts a set neural network model, and the recognition process of the intelligent recognition model for the filling fracture boundary specifically comprises the following steps:
extracting image features and spectral features according to an imaging spectral image cube in an existing database, dividing a set proportion into a training set and a test set, inputting the training set into a neural network model for training, and optimizing and verifying the trained neural network model by using the test set to obtain an optimal neural network model; inputting the image characteristics and the spectral characteristics of the target rock mass needing to be subjected to filling fracture identification into a trained neural network model to obtain a filling fracture identification result and a boundary coordinate set thereof, and combining mineral components to obtain boundary coordinates and filling mineral information of the filling fracture.
As a further scheme, checking and merging the boundary coordinates of the filled fracture and a fracture point cloud data set under a two-dimensional coordinate system, specifically:
and registering the crack point cloud data coordinates under the two-dimensional coordinate system with the boundary coordinates of the filled crack, unifying the two coordinates under the same reference coordinate system, and replacing the boundary coordinates of the filled crack with the crack point cloud data coordinates under the two-dimensional coordinate system of the corresponding position.
As a further scheme, obtaining the identification result of the rock mass fracture specifically comprises: location of the fracture, mineral filling information, and size of the fracture.
In other embodiments, the following technical solutions are adopted:
a rock mass fracture intelligent recognition system fusing three-dimensional scanning and image spectrum comprises:
the point cloud data acquisition module is used for acquiring three-dimensional point cloud data of the target rock mass through three-dimensional scanning;
the fracture point cloud data preprocessing module is used for processing the three-dimensional point cloud data, extracting discontinuous point set coordinates and carrying out dimension transformation on the extracted discontinuous point set coordinates to obtain a fracture point cloud data set under a two-dimensional coordinate system;
the image spectral data acquisition module is used for acquiring image information and spectral information of the target rock mass through spectral scanning;
the filling fracture data acquisition module is used for extracting mineral distribution characteristics based on the spectral information and extracting fracture image characteristics based on the image information; based on the mineral distribution characteristics and the fracture image characteristics, utilizing a filling fracture boundary intelligent identification model to obtain boundary coordinates of a filling fracture and filling mineral information;
and the data fusion module is used for checking and merging the boundary coordinates of the filled fracture and the fracture point cloud data set under the two-dimensional coordinate system to obtain the identification result of the rock mass fracture.
As a further scheme, the data fusion module registers the fracture point cloud data coordinates in the two-dimensional coordinate system and the boundary coordinates of the filled fracture, unifies the two coordinates in the same reference coordinate system, and replaces the boundary coordinates of the filled fracture with the fracture point cloud data coordinates in the two-dimensional coordinate system at the corresponding position.
In other embodiments, the following technical solutions are adopted:
a rock mass fracture intelligent recognition device fusing three-dimensional scanning and image spectra is used for realizing the rock mass fracture intelligent recognition method fusing three-dimensional scanning and image spectra, and is characterized in that the system comprises:
a working platform;
the electromagnetic wave receiving and transmitting device is arranged on the working platform and can transmit electromagnetic waves to the lateral rock wall, and the distance between the electromagnetic wave receiving and transmitting device and the lateral rock wall can be obtained by utilizing the back-and-forth propagation time of the electromagnetic waves so as to control the working platform to automatically move according to a set route;
the cross beams are oppositely arranged on the working platform and are respectively connected with the working platform through a lifting device; the three-dimensional scanning device and the spectrum scanning device are respectively carried on different cross beams and can rotate and translate along the cross beams; the working platform can drive the three-dimensional scanning device and the spectrum scanning device to automatically move to a set target position for data acquisition;
and the control unit is used for receiving the data acquired by the three-dimensional scanning device and the spectrum scanning device, respectively obtaining a fracture point cloud data set and a boundary coordinate data set filling the fracture based on the data, and merging the two data sets to obtain all the fractures of the target rock mass.
As a further scheme, the method further comprises the following steps: the system comprises a working platform, a miniature positioning camera, a three-dimensional scanning device and a positioning device, wherein the miniature positioning camera is arranged on the working platform, accurately positions the identification range of the rock to be detected by shooting and positioning target rock characteristic points at multiple angles, and transmits positioning information to the three-dimensional scanning device to realize region locking of the target region to be detected.
Compared with the prior art, the invention has the beneficial effects that:
(1) The invention provides a method for accurately identifying a filling fracture by adopting an image spectrum technology, and a filling fracture intelligent identification model is trained on the basis of an existing lithologic spectrum information database (the database consists of an imaging spectrum image cube, spectrum images of various minerals, corresponding spectrum numbers and molecular formulas and is combined with fracture image information characteristics) and a neural network model, so that intelligent extraction and output of a filling fracture boundary coordinate set and filling material parameters are realized, and finally, accurate identification of the filling fracture and efficient extraction of the parameters (the parameters comprise fracture shape, size, position, filling material mineral components and the like) are realized.
(2) The method is combined with a three-dimensional laser scanning technology to identify the target rock mass fracture, and the two fracture identification results are supplemented and checked mutually, so that the target rock mass fracture is comprehensively and accurately identified. The method can effectively make up the defects that the three-dimensional laser scanning cannot realize accurate identification on the filled fracture and cannot extract the filling materials, improve the data quality and greatly improve the fracture identification precision.
(3) The invention designs a rock mass fracture intelligent identification system integrating three-dimensional scanning and image spectrum, which can autonomously move to a target position for three-dimensional scanning and spectrum scanning based on a preset route, and can autonomously adjust the specific position of a scanning device, remotely control a fracture identification process, realize full-intelligent accurate identification and efficient treatment of fracture identification, and greatly improve the working efficiency of rock mass fracture identification.
Additional features and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
Drawings
FIG. 1 is a flow chart of an intelligent rock mass fracture identification method fusing three-dimensional scanning and image spectrum in the embodiment of the invention;
FIG. 2 is a flow chart of a rock mass fracture intelligent identification system integrating three-dimensional scanning and image spectra in the embodiment of the invention;
FIG. 3 is a schematic structural diagram of an intelligent rock mass fracture identification device integrating three-dimensional scanning and image spectrum in the embodiment of the invention;
FIG. 4 is a schematic diagram of height adjustment of the intelligent rock mass fracture identification device in the embodiment of the invention;
the method comprises the following steps of 1, three-dimensional laser scanner; 2. a spectral imager; 3. a cross beam; 4. a mechanical arm; 5. a hydraulic column; 6. a working platform; 7. an intelligent operation display screen; 8. a light source; 9. a miniature positioning camera; 10. a distribution box; 11. a handle; 12. a light supplement lamp; 13 electromagnetic wave transmitting and receiving means.
Detailed Description
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the disclosure. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments according to the present application. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
Example one
In one or more embodiments, the method comprises the steps of finely dividing the fracture into a filling fracture and a non-filling fracture, accurately extracting the non-filling fracture by adopting a three-dimensional scanning technology and a data processing model, carrying out fuzzy extraction on the filling fracture, accurately identifying the filling fracture by adopting an image spectrum technology, combining image characteristics and mineral distribution characteristics and combining a neural network, and supplementing and checking the filling fracture by using the image spectrum technology and the mineral distribution characteristics, wherein the image characteristics and the mineral distribution characteristics serve the respective roles, and the results supplement and check each other, so that complete, intelligent and efficient identification of full coverage of the fracture is finally realized.
With reference to fig. 1, the method of this embodiment specifically includes the following steps:
step (1): acquiring three-dimensional point cloud data of a target rock mass through three-dimensional scanning;
step (2): noise filtering processing is carried out on the three-dimensional point cloud data, discontinuous point set coordinates are extracted, dimension transformation is carried out on the extracted discontinuous point set coordinates, three-dimensional (x, y, z) coordinates of the extracted discontinuous point set are subjected to manual deletion on data in the depth (z) direction, and a fracture point cloud data set under a two-dimensional coordinate system is obtained, wherein the data set comprises a non-filled fracture point cloud data set and a filled fracture point cloud data set, and the recognition result of the filled fracture point cloud data set possibly has deviation, so that fusion merging is carried out on the two-dimensional filled fracture data set coordinates obtained through a filled fracture boundary intelligent recognition model, and accurate and comprehensive non-filled and filled point cloud fracture data sets can be obtained.
It should be noted that, in the process of acquiring the three-dimensional point cloud data, the surface of the object is measured by the three-dimensional scanning instrument, and the obtained data generally has many geometric discontinuities, which are usually expressed in the form of discrete points, called as discontinuities.
In this embodiment, processing the three-dimensional point cloud data specifically includes: point cloud intensity correction, point cloud data registration under different viewing angles, non-target point cloud filtering and the like;
the point cloud intensity correction specifically includes correcting the point cloud intensity through a preset point cloud intensity check model, and selecting the most appropriate laser incidence angle, the optimal laser scanner position and the like;
the point cloud data registration under different viewing angles is specifically to perform registration on point cloud data acquired by multiple scanning by adopting a point cloud data automatic splicing method based on reflection value images.
And (3): acquiring image information and spectral information of a target rock mass through spectral scanning;
in this embodiment, the obtained spectral information is preprocessed by variance normalization to eliminate the spectral errors between samples caused by different solid particle sizes and scattering or measuring optical paths, and the variance normalization method is as follows:
wherein, I snv For the spectral data obtained by spectral scanning, the spectral data obtained by the first scanning is set as a sample, and the variance E of the sample is calculated α And the spectral variance σ.
And (4): extracting mineral distribution characteristics based on spectral information, and extracting fracture image characteristics based on image information; based on the mineral distribution characteristics and the fracture image characteristics, utilizing a filling fracture boundary intelligent identification model to obtain boundary coordinates of a filling fracture and filling mineral information;
in this embodiment, the mineral distribution characteristics are extracted based on the spectral information, and the specific process is as follows:
acquiring a spectral curve of each pixel point in an image, determining whether the two pixel points belong to the same rock mass based on whether the spectral angles of two adjacent spectral curves are smaller than a set threshold, matching the spectral curves with a spectral database, and determining the specific mineral type corresponding to the spectral curves; thus determining the mineral type and mineral distribution situation corresponding to each pixel point, and performing mineral map filling on the basis; wherein, a spectrum curve and a mineral molecular formula matched with the spectrum curve are prestored in the spectrum database.
And performing fracture detection, filtration, point distribution, boundary line fitting, connection, correction and the like on the image information of the fractured rock mass to obtain fracture image characteristics.
And then extracting boundary coordinates of the filling fracture and outputting information of the filling minerals by using the extracted image characteristics and spectral characteristics and a trained intelligent filling fracture boundary identification model.
In this embodiment, the intelligent filling fracture boundary identification model may be implemented by using an existing neural network model, for example: the specific processing process of the deep neural network model and the filling fracture boundary intelligent recognition model on the input data is as follows:
inputting fracture image characteristics and mineral distribution characteristics obtained by processing the imaging spectrum image cube, matching fracture coordinates of the same position of a target rock body with a mineral mapping area, extracting the boundary of the overlapped area of the two areas, regarding the boundary as a filling fracture area, and finally realizing the output of the filling fracture boundary coordinates and mineral components by combining with the mineral mapping.
In this embodiment, the training process for the neural network model is as follows:
extracting the image characteristics and the spectral characteristics according to an imaging spectral image cube in an existing database, dividing the imaging spectral image cube into a training set and a test set according to the proportion of 3:1, inputting the training set into a neural network model for training, and optimizing and verifying the trained neural network model by using the test set to obtain an optimal neural network model; inputting the image characteristics and the spectral characteristics of the target rock mass needing to be subjected to filling fracture identification into a trained neural network model to obtain a filling fracture identification result and a boundary coordinate set thereof, and combining mineral components to complete the output of the filling fracture.
And (5): merging the fracture point cloud data set under the two-dimensional coordinate system and the boundary coordinates of the filled fracture to obtain all fracture parameter data of the target rock mass; the method specifically comprises the following steps: fracture shape, size, location and mineral composition of the filler.
The merging process specifically comprises the following steps: registering the two-dimensional discontinuous point set obtained through dimension transformation with the filling fracture boundary coordinate, enabling the two coordinate systems to be unified under the same reference coordinate system, determining a fracture coordinate data set with two fracture identification results at the same position by combining image information obtained through the two technologies, replacing the original fracture coordinate set with the filling fracture boundary data, and finally determining all fracture data of the target rock mass.
And carrying out secondary processing on the combined fracture boundary data, and sequentially carrying out operations such as boundary line fitting, connection, correction and the like on the fracture boundary data.
And (3) combining the distribution of filling fracture fillers, inputting the image spectrum data and the fracture data into a sketch system to realize the drawing of a rock mass fracture sketch, and realizing the one-to-one correspondence of the sketch and the fracture parameters in the drawing process so as to facilitate data calling.
Example two
In one or more embodiments, disclosed is a rock mass fracture intelligent identification system fusing three-dimensional scanning and image spectra; with reference to fig. 2, the system of this embodiment specifically includes:
and the region delineation module is used for delineating the target region to be detected, reducing redundant data acquisition and reducing the difficulty of later data processing.
The point cloud data acquisition module is used for acquiring three-dimensional point cloud data of the target rock mass through three-dimensional scanning;
the fracture point cloud data preprocessing module is used for carrying out noise filtering processing on the three-dimensional point cloud data, extracting a discontinuous point set coordinate, and carrying out dimension transformation on the extracted discontinuous point set coordinate to obtain a fracture point cloud data set under a two-dimensional coordinate system;
the image spectral data acquisition module is used for acquiring image information and spectral information of the target rock mass through spectral scanning;
the intelligent filling fracture extraction module is used for extracting mineral distribution characteristics based on spectral information and extracting fracture image characteristics based on image information; based on the mineral distribution characteristics and the fracture image characteristics, utilizing a filling fracture boundary intelligent identification model to obtain boundary coordinates of a filling fracture and filling mineral information;
and the data fusion module is used for checking and merging the crack point cloud data set and the boundary coordinates of the filled cracks to obtain the identification result of the rock mass cracks.
It should be noted that, the specific implementation method of each module is already described in the first embodiment, and is not described in detail here.
EXAMPLE III
In one or more embodiments, a rock mass fracture intelligent identification system fusing three-dimensional scanning and image spectrum is disclosed, and the system can realize the rock mass fracture intelligent identification method fusing three-dimensional scanning and image spectrum described in the first embodiment;
with reference to fig. 3, the system of this embodiment specifically includes:
two sides of the platform are respectively provided with a crossbeam 3, and the two crossbeams 3 are respectively connected with a working platform 6 through a lifting device; the three-dimensional scanning device and the spectrum scanning device are respectively carried on different cross beams, the cross beams are provided with the conveying device and the rotating shaft, and the horizontal displacement and the rotation of the three-dimensional scanning device or the spectrum scanning device can be realized through the conveying device and the rotating shaft on the cross beams.
In this embodiment, liftable device adopts hydraulic pressure post 5, can realize freely adjusting height, as shown in fig. 4, guarantees that the device on two crossbeams does not shelter from each other, still is equipped with arm 4 on the hydraulic pressure post, can realize the remote control to equipment.
The three-dimensional scanning device mainly comprises a three-dimensional laser scanner 1, the spectrum scanning device mainly comprises a light source and a spectrum imager 2, the light source 8 adopts a halogen lamp, and the brightness and the angle of the light source are adjustable.
Still be equipped with miniature location camera 9, light filling lamp 12, intelligent operation display screen 7 and other test equipment and bench thing on the work platform, miniature location camera 9 shoots the target rock mass characteristic point of location through the multi-angle and carries out the accurate positioning to the rock mass identification range that awaits measuring, passes through the sensor with locating information and synchronizes to three-dimensional laser scanner, realizes the regional locking to the target region that awaits measuring, reduces the later stage data processing degree of difficulty. The light supplement lamp 12 adopts a high-brightness LED light source to supplement light for the tunnel and other environments with insufficient light, and smooth proceeding of image data acquisition and miniature camera positioning work is guaranteed.
The working platform is provided with a shock-absorbing wear-resistant high-performance tire, so that the device can stably move; the working platform can drive the three-dimensional scanning device and the spectrum scanning device to move to a set target position for data acquisition.
The electromagnetic wave transceiver 13 emits electromagnetic waves through a built-in pulse generator, and the distance between the electromagnetic wave transceiver and the surrounding rock wall is obtained by utilizing the number of pulses of the pulse back-and-forth propagation time interval on a measuring line, so that the working platform can be controlled to automatically run on a given route. The apparatus also includes a power distribution box 10, which is intended to provide power to the entire apparatus, with the purpose of making the power available for proper distribution.
The device also includes a handle 11 for short-range device transport and manual position adjustment.
The system of the embodiment further comprises: and the control unit is used for receiving the data acquired by the three-dimensional scanning device and the spectrum scanning device, respectively obtaining a non-filled fracture point cloud data set and a filled fracture boundary coordinate data set based on the data, and merging the two data sets to obtain all fractures of the target rock mass.
The specific working process of the control unit is consistent with the method disclosed in the first embodiment, and the control unit mainly comprises the following components:
(1) A data collection and processing system: the device consists of a data collection module and a data processing module. The data collection module is responsible for receiving data such as images, spectrums, point clouds and the like acquired by the fracture scanning integrated system, and classifying, transferring and the like the data; the data processing module consists of a spectrum data processing unit and a point cloud data processing unit. The spectral data processing unit firstly carries out preprocessing and image and mineral characteristic extraction on spectral information, and then inputs the extracted characteristics into the intelligent crack filling identification model. And the intelligent identification model of the filling fracture extracts a boundary coordinate set of the filling fracture and outputs parameters of the filler by utilizing a neural network through the extracted image characteristics and spectral characteristics. The point cloud data processing unit inputs the point cloud data and the image data into the intelligent point cloud data processing model and processes the point cloud data. The point cloud data intelligent processing model can sequentially carry out point cloud data including point cloud intensity correction, point cloud data registration under different visual angles, non-target point cloud filtering and discontinuous point set coordinate extraction, and on the basis, depth dimension elimination is carried out on the obtained coordinate set to realize dimension conversion of coordinates.
(2) Data merge and storage system: the system consists of a data integration module and a storage module; and the data integration module merges the received filled fracture boundary coordinate data set after data processing and the fracture point cloud data after dimension conversion and codes the fracture, and realizes pairing of the filled fracture and the filler. Merging processing is carried out to realize coordinate registration, coordinate checking, coordinate elimination and coordinate combination on two-dimensional coordinate sets with different sources, and merged fracture boundary coordinate data are input into a rock mass fracture output system after secondary processing is carried out on the merged fracture boundary coordinate data; the data storage module is used for storing data information and program information so as to facilitate data migration backup analysis and program upgrade detection and repair.
(3) Rock mass crack output system: the device consists of a rock fracture sketch module and a fracture parameter output module; the rock mass fracture sketch module inputs fracture data into fracture sketch software, realizes imaging description and output of rock mass fractures, and performs detailed drawing on each fracture. The fracture output module is composed of a fracture output unit and a liquid crystal display, the fracture output unit is used for matching and outputting fracture images and parameter data, the fracture images and the parameter data are finally displayed by the liquid crystal display, and functions of system control, fracture data query and extraction and the like can be achieved through the display screen. The output parameter information mainly comprises: the position, shape and size of the crack, and mineral composition for filling the crack filler;
(4) The intelligent control system comprises: the intelligent control system can carry out remote control to the system, realizes opening and stopping and attitude adjustment to spectrometer and three-dimensional laser scanner through the wireless signal transceiver among the control unit and sensor, realizes the freedom adjustment of conveyer and pivot, light source on arm, the crossbeam, realizes the control to electromagnetic wave transceiver, guarantees the accurate removal of device. And the optimal scheduling and reasonable configuration of each system and supporting facilities are realized. The remote operation of the mobile terminal in the process and the checking and extraction of the crack and the parameter information can be realized by combining an intelligent control system with a remote control platform.
Although the embodiments of the present invention have been described with reference to the accompanying drawings, it is not intended to limit the scope of the present invention, and it should be understood by those skilled in the art that various modifications and variations can be made without inventive efforts by those skilled in the art based on the technical solution of the present invention.
Claims (10)
1. A rock mass fracture intelligent identification method integrating three-dimensional scanning and image spectra is characterized by comprising the following steps:
acquiring three-dimensional point cloud data of a target rock mass through three-dimensional scanning;
processing the three-dimensional point cloud data, extracting a discontinuous point set coordinate, and performing dimension transformation on the extracted discontinuous point set coordinate to obtain a fracture point cloud data set under a two-dimensional coordinate system;
acquiring image information and spectral information of a target rock mass through spectral scanning;
extracting mineral distribution characteristics based on spectral information, and extracting fracture image characteristics based on image information; based on the mineral distribution characteristics and the fracture image characteristics, utilizing a filling fracture boundary intelligent identification model to obtain boundary coordinates of a filling fracture and filling mineral information;
and checking and merging the boundary coordinates of the filled fracture and the fracture point cloud data set under the two-dimensional coordinate system to obtain the identification result of the rock mass fracture.
2. The intelligent rock mass fracture identification method integrating three-dimensional scanning and image spectroscopy as claimed in claim 1, wherein after the three-dimensional point cloud data is processed and the discontinuous point set coordinates are extracted, dimension transformation is performed on the extracted discontinuous point set coordinates, and the specific process is as follows: and manually deleting the data in the z direction of the three-dimensional (x, y, z) coordinates of the extracted discontinuous point set, and converting the data into a fracture point cloud data set in a two-dimensional coordinate system.
3. The intelligent rock mass fracture identification method integrating three-dimensional scanning and image spectroscopy as claimed in claim 1, wherein the mineral distribution characteristics are extracted based on spectral information, and the specific process is as follows:
acquiring a spectral curve of each pixel point in an image, determining whether the two pixel points belong to the same rock mass based on whether the spectral angles of two adjacent spectral curves are smaller than a set threshold, matching the spectral curves with a spectral database, and determining the specific mineral type corresponding to the spectral curves; determining the mineral type and mineral distribution condition corresponding to each pixel point, and performing mineral map filling; wherein, a spectrum curve and a mineral molecular formula matched with the spectrum curve are prestored in the spectrum database.
4. The intelligent rock mass fracture identification method integrating three-dimensional scanning and image spectroscopy as claimed in claim 1, wherein the intelligent filling fracture boundary identification model adopts a set neural network model, and for the identification process of the intelligent filling fracture boundary identification model, the method specifically comprises:
extracting image features and spectral features according to an imaging spectral image cube in an existing database, dividing a set proportion into a training set and a test set, inputting the training set into a neural network model for training, and optimizing and verifying the trained neural network model by using the test set to obtain an optimal neural network model; inputting the image characteristics and the spectral characteristics of the target rock mass needing to be subjected to filling fracture identification into a trained neural network model to obtain a filling fracture identification result and a boundary coordinate set thereof, and combining mineral components to obtain the boundary coordinates of the filling fracture and filling mineral information.
5. The intelligent rock mass fracture identification method integrating three-dimensional scanning and image spectroscopy as claimed in claim 1, wherein the boundary coordinates of the filled fracture and the fracture point cloud data set under the two-dimensional coordinate system are checked and merged, specifically:
and registering the crack point cloud data coordinates in the two-dimensional coordinate system and the boundary coordinates of the filled cracks, unifying the two coordinates in the same reference coordinate system, and replacing the boundary coordinates of the filled cracks with the crack point cloud data coordinates in the two-dimensional coordinate system at the corresponding position.
6. The intelligent rock mass fracture identification method integrating three-dimensional scanning and image spectroscopy as claimed in claim 1, wherein obtaining the identification result of the rock mass fracture specifically comprises: location of the fracture, mineral filling information, and size of the fracture.
7. The utility model provides a fuse rock mass crack intelligent recognition system of three-dimensional scanning and image spectrum which characterized in that includes:
the point cloud data acquisition module is used for acquiring three-dimensional point cloud data of the target rock mass through three-dimensional scanning;
the fracture point cloud data preprocessing module is used for processing the three-dimensional point cloud data, extracting a discontinuous point set coordinate, and performing dimension transformation on the extracted discontinuous point set coordinate to obtain a fracture point cloud data set under a two-dimensional coordinate system;
the image spectral data acquisition module is used for acquiring image information and spectral information of the target rock mass through spectral scanning;
the filling fracture data acquisition module is used for extracting mineral distribution characteristics based on the spectral information and extracting fracture image characteristics based on the image information; based on the mineral distribution characteristics and the fracture image characteristics, utilizing a filling fracture boundary intelligent identification model to obtain boundary coordinates of a filling fracture and filling mineral information;
and the data fusion module is used for checking and merging the boundary coordinates of the filled fracture and the fracture point cloud data set under the two-dimensional coordinate system to obtain the identification result of the rock mass fracture.
8. The system for intelligently identifying the rock mass fracture integrating the three-dimensional scanning and the image spectrum as claimed in claim 7, wherein the data fusion module registers the data coordinates of the fracture point cloud under the two-dimensional coordinate system with the coordinates of the boundary of the filled fracture, unifies the two coordinates under the same reference coordinate system, and replaces the coordinates of the boundary of the filled fracture with the coordinates of the fracture point cloud under the two-dimensional coordinate system at the corresponding position.
9. A rock mass fracture intelligent identification system fusing three-dimensional scanning and image spectra, which is used for realizing the rock mass fracture intelligent identification method fusing three-dimensional scanning and image spectra, which is characterized by comprising the following steps of:
a working platform;
the electromagnetic wave receiving and transmitting device is arranged on the working platform and can transmit electromagnetic waves to the lateral rock wall, and the distance between the electromagnetic wave receiving and transmitting device and the lateral rock wall can be obtained by utilizing the back-and-forth propagation time of the electromagnetic waves so as to control the working platform to automatically move according to a set route;
the cross beams are oppositely arranged on the working platform and are respectively connected with the working platform through a lifting device; the three-dimensional scanning device and the spectrum scanning device are respectively carried on different cross beams and can rotate and translate along the cross beams; the working platform can drive the three-dimensional scanning device and the spectrum scanning device to automatically move to a set target position for data acquisition;
and the control unit is used for receiving the data acquired by the three-dimensional scanning device and the spectrum scanning device, respectively obtaining a fracture point cloud data set and a boundary coordinate data set for filling the fracture based on the data, and merging the two data sets to obtain all the fractures of the target rock mass.
10. The intelligent rock mass fracture identification system integrating three-dimensional scanning and image spectroscopy as claimed in claim 9, further comprising: the system comprises a working platform, a miniature positioning camera, a three-dimensional scanning device and a positioning device, wherein the miniature positioning camera is arranged on the working platform, accurately positions the identification range of the rock to be detected by shooting and positioning target rock characteristic points at multiple angles, and transmits positioning information to the three-dimensional scanning device to realize region locking of the target region to be detected.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211291423.4A CN115753643A (en) | 2022-10-19 | 2022-10-19 | Rock mass fracture intelligent identification method and system integrating three-dimensional scanning and image spectrum |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211291423.4A CN115753643A (en) | 2022-10-19 | 2022-10-19 | Rock mass fracture intelligent identification method and system integrating three-dimensional scanning and image spectrum |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115753643A true CN115753643A (en) | 2023-03-07 |
Family
ID=85352515
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211291423.4A Pending CN115753643A (en) | 2022-10-19 | 2022-10-19 | Rock mass fracture intelligent identification method and system integrating three-dimensional scanning and image spectrum |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115753643A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116309807A (en) * | 2023-04-04 | 2023-06-23 | 中南大学 | Core ground repositioning system based on digital image intelligent recognition |
| CN117218448A (en) * | 2023-09-28 | 2023-12-12 | 西安科技大学 | Coal and rock identification method based on Bayesian model fusion geological information |
| CN118171351A (en) * | 2024-03-07 | 2024-06-11 | 山东大学 | Tunnel twin virtual body modeling method and system based on multi-source data driving |
| CN118397209A (en) * | 2024-06-27 | 2024-07-26 | 河北华勘地质勘查有限公司 | Visualization method and system for mine goaf measurement data |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111189864A (en) * | 2020-01-13 | 2020-05-22 | 中国石油天然气股份有限公司 | EPMA-WDX full-rock mineral identification and plane imaging method and device |
| CN112348880A (en) * | 2020-11-10 | 2021-02-09 | 重庆科技学院 | Construction method of unconventional reservoir multi-scale and multi-component digital core |
| CN113191330A (en) * | 2021-05-27 | 2021-07-30 | 宜宾学院 | Method for identifying area growth pores by fusing secondary electrons and back scattering electron images |
| CN113609696A (en) * | 2021-08-16 | 2021-11-05 | 中国地质大学（北京） | Multi-scale multi-component digital core construction method and system based on image fusion |
| CN114418965A (en) * | 2021-12-29 | 2022-04-29 | 西南石油大学 | Outcrop crack identification method based on laser radar technology |
| CN114648563A (en) * | 2022-03-24 | 2022-06-21 | 中国石油大学(华东) | Registration method of core CT scanning image and spliced SEM image |
| CN114894814A (en) * | 2022-03-24 | 2022-08-12 | 佛山市公路桥梁工程监测站有限公司 | Bridge and culvert detection method, computer and equipment |
| CN115019010A (en) * | 2022-06-23 | 2022-09-06 | 江苏燕宁工程科技集团有限公司 | Tunnel structure disease display method based on three-dimensional laser scanning and BIM technology |
-
2022
- 2022-10-19 CN CN202211291423.4A patent/CN115753643A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111189864A (en) * | 2020-01-13 | 2020-05-22 | 中国石油天然气股份有限公司 | EPMA-WDX full-rock mineral identification and plane imaging method and device |
| CN112348880A (en) * | 2020-11-10 | 2021-02-09 | 重庆科技学院 | Construction method of unconventional reservoir multi-scale and multi-component digital core |
| CN113191330A (en) * | 2021-05-27 | 2021-07-30 | 宜宾学院 | Method for identifying area growth pores by fusing secondary electrons and back scattering electron images |
| CN113609696A (en) * | 2021-08-16 | 2021-11-05 | 中国地质大学（北京） | Multi-scale multi-component digital core construction method and system based on image fusion |
| CN114418965A (en) * | 2021-12-29 | 2022-04-29 | 西南石油大学 | Outcrop crack identification method based on laser radar technology |
| CN114648563A (en) * | 2022-03-24 | 2022-06-21 | 中国石油大学(华东) | Registration method of core CT scanning image and spliced SEM image |
| CN114894814A (en) * | 2022-03-24 | 2022-08-12 | 佛山市公路桥梁工程监测站有限公司 | Bridge and culvert detection method, computer and equipment |
| CN115019010A (en) * | 2022-06-23 | 2022-09-06 | 江苏燕宁工程科技集团有限公司 | Tunnel structure disease display method based on three-dimensional laser scanning and BIM technology |
Non-Patent Citations (3)
| Title |
|---|
| 姚骏屏;王卫星;: "一种基于图像融合的岩石裂隙充填物分割方法", 重庆邮电学院学报(自然科学版), no. 01, 28 February 2006 (2006-02-28) * |
| 孙刚;: "基于显微CT扫描的膨胀岩土体的裂隙结构与分形特征研究", 化工矿物与加工, no. 09, 20 September 2018 (2018-09-20) * |
| 潘东东: "考虑剪切接触与碎屑充填的裂隙渗流模型与数值分析", 中南大学学报(自然科学版), vol. 50, no. 7, 31 July 2019 (2019-07-31) * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116309807A (en) * | 2023-04-04 | 2023-06-23 | 中南大学 | Core ground repositioning system based on digital image intelligent recognition |
| CN116309807B (en) * | 2023-04-04 | 2024-04-26 | 中南大学 | Core ground repositioning system based on digital image intelligent recognition |
| CN117218448A (en) * | 2023-09-28 | 2023-12-12 | 西安科技大学 | Coal and rock identification method based on Bayesian model fusion geological information |
| CN117218448B (en) * | 2023-09-28 | 2024-08-27 | 西安科技大学 | Coal and rock identification method based on Bayesian model fusion geological information |
| CN118171351A (en) * | 2024-03-07 | 2024-06-11 | 山东大学 | Tunnel twin virtual body modeling method and system based on multi-source data driving |
| CN118397209A (en) * | 2024-06-27 | 2024-07-26 | 河北华勘地质勘查有限公司 | Visualization method and system for mine goaf measurement data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115753643A (en) | Rock mass fracture intelligent identification method and system integrating three-dimensional scanning and image spectrum | |
| US11634987B2 (en) | Safety early warning method and device for full-section tunneling of tunnel featuring dynamic water and weak surrounding rock | |
| US12013485B2 (en) | Multi-scale inspection and intelligent diagnosis system and method for tunnel structural defects | |
| Assali et al. | Surveying and modeling of rock discontinuities by terrestrial laser scanning and photogrammetry: Semi-automatic approaches for linear outcrop inspection | |
| CN104502990A (en) | Geological survey method of tunnel face based on digital image | |
| US11796493B2 (en) | System and method for identifying lithology based on images and XRF mineral inversion | |
| CN112446852B (en) | Tunnel imaging plane display method and defect intelligent recognition system | |
| CN113256599B (en) | Method for detecting hydraulic tunnel defects based on three-dimensional dynamic model | |
| CN108564628A (en) | A kind of cutterhead vision positioning orientation system towards development machine automation | |
| CN115877400A (en) | Tunnel roof support steel belt drilling positioning method based on radar and vision fusion | |
| WO2021043308A1 (en) | Image identification and analysis-based system and method for predicting quartz content of surrounding rock in tunnel | |
| CN114898053A (en) | Three-dimensional space image technology-based fractured loose rock mass development range delineation method | |
| US20220284671A1 (en) | System and method for collecting and georeferencing 3d geometric data associated with a gps-denied environment | |
| CN117804368B (en) | Tunnel surrounding rock deformation monitoring method and system based on hyperspectral imaging technology | |
| CN109696156A (en) | Tunnel tunnel face geological information fast acquiring method based on close-range photogrammetry | |
| CN114943890A (en) | Transformer substation field flatness identification method adopting unmanned aerial vehicle-mounted laser point cloud | |
| CN112700423A (en) | Method and system for automatically detecting surface damage defects of fuselage based on deep learning | |
| KR102481914B1 (en) | Apparatus for obtaining 3D spatial information of underground facilities using cell phone lidar and photos and method for obtaining 3D spatial information of underground facilities using the same | |
| CN115601517A (en) | Rock mass structural plane information acquisition method and device, electronic equipment and storage medium | |
| Chen et al. | A non-contact measurement method for rock mass discontinuity orientations by smartphone | |
| CN115641453A (en) | Hyperspectral technology-based tunnel surrounding rock weathering degree identification method and system | |
| CN116226965A (en) | Building waste estimation algorithm based on BIM | |
| CN105592294A (en) | VSP excited cannon group monitoring system | |
| CN111060918A (en) | Dry beach monitoring method based on photogrammetry and laser ranging | |
| CN116840042A (en) | Real-time surrounding rock grading device for multi-source data fusion and using method |
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 |