CN115661133B - Geological type identification method - Google Patents
Geological type identification method Download PDFInfo
- Publication number
- CN115661133B CN115661133B CN202211563539.9A CN202211563539A CN115661133B CN 115661133 B CN115661133 B CN 115661133B CN 202211563539 A CN202211563539 A CN 202211563539A CN 115661133 B CN115661133 B CN 115661133B
- Authority
- CN
- China
- Prior art keywords
- tool mark
- mark
- drill bit
- tool
- density
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 51
- 239000011435 rock Substances 0.000 claims abstract description 49
- 238000012216 screening Methods 0.000 claims description 22
- 238000004422 calculation algorithm Methods 0.000 claims description 16
- 230000035772 mutation Effects 0.000 claims description 15
- 230000015572 biosynthetic process Effects 0.000 claims description 12
- 230000005641 tunneling Effects 0.000 claims description 11
- 238000004364 calculation method Methods 0.000 claims description 8
- 238000013507 mapping Methods 0.000 claims description 6
- 230000011218 segmentation Effects 0.000 claims description 4
- 230000003595 spectral effect Effects 0.000 claims description 4
- 238000007621 cluster analysis Methods 0.000 claims description 3
- 230000000877 morphologic effect Effects 0.000 description 7
- 230000002146 bilateral effect Effects 0.000 description 3
- 239000004927 clay Substances 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 238000010276 construction Methods 0.000 description 3
- 238000001914 filtration Methods 0.000 description 3
- 238000005286 illumination Methods 0.000 description 3
- 239000004576 sand Substances 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 239000000428 dust Substances 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 239000000779 smoke Substances 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 241001391944 Commicarpus scandens Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000739 chaotic effect Effects 0.000 description 1
- 238000005056 compaction Methods 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 238000013467 fragmentation Methods 0.000 description 1
- 238000006062 fragmentation reaction Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
Images
Landscapes
- Geophysics And Detection Of Objects (AREA)
Abstract
The invention relates to the technical field of graphic data identification, in particular to a geological type identification method. According to the method, the cutter mark image data formed on the rock body by the drill bit in the working process of the rock breaking machine are collected, the concentric circle significance and cutter mark compactness are obtained according to the collected cutter mark image data, the stratum geological compactness is further represented through the concentric circle significance and the cutter mark compactness, and the identification of the geological type is completed according to the stratum geological compactness. According to the invention, the overall characteristics of the tool mark image are represented according to the significance of the concentric circles, the local characteristics of the tool mark image are represented according to the density of the tool marks, and the identification of the geological type is accurately completed by combining the whole with the local, and the geological type is identified according to the tool mark image formed on the rock body by the drill bit, so that the cost is lower compared with the prior art. Therefore, the invention has lower cost while ensuring the accuracy.
Description
Technical Field
The invention relates to the technical field of graphic data identification, in particular to a geological type identification method.
Background
Before mining, tunnel construction and geological exploration, the geological environment of the construction needs to be explored in advance, but the geological situation is often complex and changeable, and the acquired geological information has a plurality of limitations and inaccuracy, so that the real-time geological information in the tunneling process needs to be analyzed.
The geological type identification method in the prior art mainly comprises the following steps: in the working process of the rock breaker, the geological type is judged according to the vertical stress condition of the hob of the rock breaker. However, the method for judging the geological type according to the vertical stress condition of the hob of the rock breaker requires that a device for detecting the hob strength is arranged on each hob, and has higher cost; and the geological type can be judged inaccurately only according to the stress condition, so that the method for judging the geological type according to the vertical stress condition of the rock breaker hob is high in cost and inaccurate. In the prior art, the geological image can be identified through the neural network, but the method for identifying through the neural network needs to manually label a large amount of geological historical data, so that the cost is high, and the identification accuracy is low under the condition that the historical data is insufficient.
Disclosure of Invention
In order to solve the technical problems, the invention aims to provide a geological type identification method, which adopts the following technical scheme:
the invention provides a geological type identification method, which comprises the following steps:
acquiring a denoised face image generated by tunneling of a rock breaker, taking a part of the face image, the gray value of which is larger than a preset first threshold value, as a first screening area, wherein the first screening area comprises a plurality of connected areas, and screening out drill bit tool mark subareas of the connected areas according to the fitting degree of the connected areas and circles;
obtaining a circle center of a corresponding drill bit tool mark subarea according to the fitting circle corresponding to each drill bit tool mark subarea, and obtaining a tool mark concentric circle significance according to the position distribution characteristics among the circle centers of the drill bit tool mark subareas and the number of the drill bit tool mark subareas;
obtaining the width of the cutter mark at each position of the cutter mark subregion of the drill bit, detecting the quantity of corner points of the cutter mark subregion of the drill bit, and obtaining the density of the cutter mark according to the width distribution characteristics of the width of the cutter mark and the quantity of the corner points;
and obtaining stratum geological density according to the tool mark concentric circle significance and the tool mark density, and completing identification of geological types according to the stratum geological density.
Further, the method for acquiring the position distribution characteristics comprises the following steps:
calculating Euclidean distances between circle centers of the cutter mark subregions of each drill bit, calculating standard deviation of the Euclidean distances, and screening mutation values through a BG segmentation algorithm after the Euclidean distances are arranged from small to large; calculating a first mean value of the mutation values and screening a second mean value corresponding to other Euclidean distances except the mutation values, and obtaining a convex hull formed by circle centers of the drill bit tool mark subregions according to a convex hull algorithm to obtain the area of the convex hull; if the mutation value does not exist, the first average value and the second average value are equal;
and taking the standard deviation, the first mean value, the second mean value and the area of the convex hull as the position distribution characteristics.
Further, the obtaining the significance of the concentric circles of the tool marks according to the position distribution characteristics between circle centers of the tool mark subregions of the drill bit and the number of the tool mark subregions of the drill bit comprises:
obtaining the tool mark concentric circle saliency through a tool mark concentric circle saliency calculation model according to the position distribution characteristics among the circle centers of the tool mark subregions of the drill bit and the number of the tool mark subregions of the drill bit, wherein the tool mark concentric circle saliency calculation model comprises:
wherein ,
for the significance of the concentric circles of the tool marks, +.>
For said first mean,/a>
For said second mean,/>
For the area of the convex hull, +.>
Is the standard deviation of the Euclidean distance, < >>
For the number of bit tool mark subregions, < >>
Is a preset adjustment coefficient.
Further, the width distribution feature of the tool mark width includes:
constructing a three-dimensional coordinate system based on the positions of pixel points in the drill bit tool mark sub-area and the tool mark widths corresponding to the pixel points, wherein the x-axis of the three-dimensional coordinate system is the transverse axis of an image coordinate system, the y-axis is the longitudinal axis of the image coordinate system, and the z-axis is the tool mark width; mapping each pixel point in the drill bit tool mark subarea to the three-dimensional coordinate system; clustering pixel points in the three-dimensional coordinate system by a clustering algorithm in the three-dimensional coordinate system to obtain a pixel point clustering set; and taking the difference between the width of each tool mark and the average value of the width of the tool mark and the number of the pixel point clustering sets as the width distribution characteristics of the width of the tool mark.
Further, the obtaining the tool mark density according to the width distribution feature of the tool mark width and the number of corner points includes:
cutter mark density is obtained through a cutter mark density model according to the cutter mark width distribution characteristics, the corner number and the pixel point clustering set, and the cutter mark density model comprises:
wherein ,
for the compactness of the tool mark, +.>
Is->
Width of each tool mark->
Is the average value of the width of the tool mark, +.>
For the number of corner points +.>
For the number of clusters of pixels, < >>
Is the number of rays.
Further, the obtaining the formation geological density according to the tool mark concentric circle significance and the tool mark density comprises:
accumulating the tool mark density to obtain a tool mark density accumulated value, mapping the tool mark density accumulated value into an exponential function based on a natural constant, and taking the product of the mapped value and the corresponding concentric circle significance as the stratum geological density.
Further, the identifying of the geological type according to the stratum geological density comprises the following steps:
the stratum with stratum geological density larger than a first preset density threshold is divided into hard rock stratum, the stratum with stratum smaller than a second preset density threshold is divided into soft stratum, the stratum with stratum smaller than or equal to the first preset density threshold and larger than or equal to the second preset density threshold is divided into uneven soft and hard stratum, and the first preset density threshold is larger than the second preset density threshold.
Further, the filtering the drill bit tool mark sub-area of the communication domain according to the fitting degree of the communication domain and the circle comprises:
and marking the region where the pixel point set corresponding to the circle fitting degree larger than the preset fitting degree threshold value is located as a drill bit tool mark sub-region.
Further, the obtaining the width of the tool mark at each position of the tool mark sub-region of the drill bit includes:
and taking the circle center of the fitting circle corresponding to the drill bit tool mark subarea as a starting point to obtain rays in all directions, and taking the length of a line segment of the rays in the edge of the drill bit tool mark subarea as the tool mark width.
Further, the connected domain obtaining method in the first screening area includes:
and carrying out cluster analysis on the pixel points contained in the first screening area by using a spectral clustering algorithm to obtain a plurality of connected areas.
The invention has the following beneficial effects:
according to the embodiment of the invention, the significance of the concentric circles of the tool marks is obtained according to the difference between the centers of the tool mark subregions of the drill bit and the number of the tool mark subregions of the drill bit, the significance of the concentric circles of the tool marks formed by the drill bit of the rock breaker is used as one parameter for judging the geological type, the compactness of the tool marks is obtained according to the width and the number of the corner points of the tool marks and the corresponding clustering set of the pixel points, and the compactness of the tool marks is used as the other parameter for judging the geological type. The concentric circle saliency represents the integral distribution of the tool mark subregions, the tool mark density represents the specific shape characteristics of each tool mark subregion, the integral tool mark morphological characteristics of the face image, namely the bottom geological density, are obtained by combining the concentric circle saliency with the tool mark density, and geology can be identified through the integral tool mark morphological characteristics in the image. According to the embodiment of the invention, the geological type identification is carried out only according to the tool mark image formed by the drill bit, compared with the existing method, the cost is lower, and the tool mark morphological characteristics are further specifically represented by combining two parameters of the concentric circle saliency and the tool mark saliency, so that the integral distribution of the tool mark subareas is represented, the specific shape characteristics of each tool mark subarea are also represented, and the geological type identification is more accurate. In summary, in the process of identifying the geological type, the accuracy of identifying the geological type is improved while the cost is low.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions and advantages of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flowchart of a method for identifying a geologic type according to an embodiment of the invention.
Fig. 2 is a sectional image of a rock breaker tunnelling.
Detailed Description
In order to further describe the technical means and effects adopted by the present invention to achieve the preset purpose, the following detailed description refers to a specific implementation, structure, characteristics and effects of a geological type identification method according to the present invention with reference to the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
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 invention belongs.
The following specifically describes a specific scheme of a geological type identification method provided by the invention with reference to the accompanying drawings.
Referring to fig. 1, a flowchart of a geological type identification method according to an embodiment of the present invention is shown, where the method includes:
step S1: and acquiring a denoised face image generated by tunneling of the rock breaker, taking a part of the face image, the gray value of which is larger than a preset first threshold value, as a first screening area, wherein the first screening area comprises a plurality of connected areas, and screening out drill bit tool mark subareas of the connected areas according to the fitting degree of the connected areas and circles.
Erecting a camera at the tunneling section of the rock breaker, and shooting by the camera in the tunneling process of the rock breaker to obtain a tunnel face image of the tunneling section, wherein the tunnel face image is an RGB image. Meanwhile, the rock breaker is positioned in a mountain or a rock body in the tunneling process, so that the environment is dim, and extra illumination is needed to be provided when a camera is used for shooting the face of the tunneling section. In the embodiment of the invention, the camera is selected as a CCD camera, and the adopted illumination equipment can make the face image shot by the camera clear enough, and the invention is not limited further.
Further, in the tunneling process of the rock breaker, smoke dust is necessarily generated due to the fragmentation of the rock mass, and the smoke dust can cause unavoidable noise of the face image shot by the camera, so that the quality of the face image is further affected, and denoising treatment is needed for the face image which is initially acquired by the camera. Image denoising is a common prior art in image processing, and denoising methods that may be employed herein include, but are not limited to, smoothing filter denoising techniques, median filter denoising techniques, bilateral filter denoising techniques, and the like. In the embodiment of the invention, the acquired face line is subjected to denoising pretreatment by adopting a bilateral filtering denoising technology to obtain a denoised face image. According to the embodiment of the invention, only the acquired face image is analyzed, and professional data acquisition equipment is not needed, so that the cost of the method for identifying the geological type according to the image is lower compared with that of the prior art. It should be noted that, the face images processed later are all denoised face images, and the bilateral filtering denoising technology is a prior art well known to those skilled in the art, and is not further limited and detailed herein.
Referring to fig. 2, a sectional image of tunneling of a rock breaker according to an embodiment of the present invention is shown, and as can be seen from fig. 2, a plurality of drill bits are provided on a section of the rock breaker, and during operation of the rock breaker, a plurality of circular tool marks are formed on a surface of a stratum by rotating and rubbing each drill bit on the surface of the rock breaker, and the circular tool marks are similar to concentric circles. After the denoised face image is obtained, the tool marks formed by the drill bit of the rock breaker in the face image are analyzed, and the tool marks formed by the drill bit are concentric, but when the rock breaker breaks a natural rough rock body, different protrusions or recesses are generated at different positions, and the reflection degree of the different positions is further caused to be mistakenly divided into the tool marks in the concentric circles, so that the denoised face image is further screened to prevent the influence of the reflection degree of the different positions on the tool mark analysis.
In the embodiment of the invention, in order to facilitate subsequent calculation, the graying treatment of the face image is performed, and the area with the gray value larger than the preset first threshold value is selected as the first screening area. In the embodiment of the invention, the tunnel face image is initially divided by using an OTSU maximum inter-class variance method, namely, a first threshold value is obtained by using the OTSU maximum inter-class variance method.
Carrying out cluster analysis on the pixel points contained in the first screening area by using a spectral clustering algorithm to obtain a plurality of pixel point cluster sets, and recording the number of the pixel point cluster sets as
，/>
And the pixel point sets are positive integers, and different pixel point sets correspond to different connected domains.
It should be noted that, the OTSU maximum inter-class variance method and the spectral clustering algorithm are well known to those skilled in the art, and the first preset threshold is specifically set according to different illumination degrees, which are not further limited and described herein.
Fitting all pixel points contained in different connected domains with circles so that each different connected domain corresponds to different fitting degrees of the circles, and obtaining the fitting degrees of the circles comprises an equation for fitting the circles and the fitting goodness of the circles. Further screening the fitting degree of circles corresponding to different connected domains by setting a fitting degree threshold value, wherein the fitting degree is larger than the fitting degree threshold value
The communicating areas are screened out, the screened communicating areas correspond to the tool marks formed by the drill bit, each screened communicating area is marked as a tool mark subarea of the drill bit, and the number of the screened communicating areas is marked as +.>
Namely the number of the corresponding bit tool mark subareas is +.>
，/>
Is a positive integer. In the embodiment of the invention, the fitness threshold value is +.>
Set to 0.82. It should be noted that, the technical means for obtaining the fitting circle corresponding to the connected domain through the pixel point distribution of the connected domain is known in the prior art by those skilled in the art, and is not further limited and described herein.
And S2, obtaining the circle centers of the corresponding drill bit tool mark subareas according to the fitting circles corresponding to the drill bit tool mark subareas, and obtaining the significance of the concentric circles of the tool marks according to the position distribution characteristics among the circle centers of the drill bit tool mark subareas and the number of the drill bit tool mark subareas.
Because the tool marks formed by the rock breaker are concentric circles, the distribution characteristics of circles corresponding to the obtained different tool mark subregions and the significance of the tool marks screened according to the brightness characteristics displayed in the image on the displayed concentric circle characteristics are further analyzed.
The stratum types of the working face of the rock breaker can be divided according to the structure compactness degree or the looseness degree of the stratum, and are mainly divided into hard rock stratum, uneven soft and hard stratum and soft bottom layers. The hard rock stratum is high in structural compactness and hardness, the tool marks formed on the hard rock stratum by the rock breaker drill bit during operation are clear and obvious, the same tool mark is not easy to break, the drill bit tool mark areas are obvious and the number of drill bit tool mark subareas is large on the corresponding image of the corresponding hard rock stratum, and the concentric circle characteristics of the corresponding drill bit tool mark areas are more obvious. The stratum with uneven hardness is mainly a composite stratum, the position dug by the rock breaker contains various rock and soil, the mechanical property and the geology are greatly different, the corresponding position with high hardness has clear tool marks, the position with loose structure presents the condition that the tool mark is blurred and difficult to identify, so that the concentric circle characteristics corresponding to the tool mark area of the drill bit have certain explicit and dominant characteristics on the image corresponding to the stratum with uneven hardness. The soft bottom layer is mainly a clay layer, a sand-containing water-rich layer and other soft layers, the corresponding layers are loose in structure, collapse and mud cake formation and other conditions can occur near the tool marks of the rock breaker drill bit in the working process, and the corresponding tool marks are loose, so that concentric circle features corresponding to the tool mark areas of the drill bit are not obvious in images corresponding to the soft bottom layer. The formation class can be further identified based on the different concentric circle saliency.
The significance of the concentric circles of the drill bit tool mark area is required to be characterized together according to the circle center position distribution characteristics of different drill bit tool mark subareas and the number of the drill bit tool mark subareas. When the circle center position distribution of each drill bit tool mark subarea is more discrete and the number of the tool mark subareas is smaller, the corresponding structure compactness degree and hardness of the stratum are lower; in contrast, when the center positions of the tool mark subareas of each drill bit are distributed more densely and the number of the tool mark subareas is larger, the corresponding stratum is higher in structural compactness and hardness.
The method for specifically obtaining the circle center distribution characteristics of the tool mark subregion comprises the following steps: firstly, calculating Euclidean distances between circle centers of equations of all circles obtained by fitting corresponding to each drill bit tool mark subarea, calculating standard deviations of Euclidean distance values, arranging all Euclidean distances into a group of sequences from small to large, screening mutation values in the sequences through a BG segmentation algorithm, marking the average value of the mutation values as a first average value, and marking the average value of other values except the mutation values in the sequences as a second average value. It should be noted that, when no mutation value is screened in the set of sequences, the value of the first mean value is assigned as the second mean value, and the BG segmentation algorithm is a prior art well known to those skilled in the art, which is not further limited and described herein.
When the region in the image corresponding to the tool mark presents a concentric circle to a higher degree, the distance between the circle centers of the corresponding tool mark subregions of the drill bit is relatively close, the corresponding Euclidean distance is small, the distribution of values is relatively centralized and uniform, no abrupt change value appears in the formed sequence, and when the abrupt change value appears in the sequence, the drill bit tool mark subregion corresponding to the abrupt change valueThe circle center of the domain has large difference with the circle center positions corresponding to other tool mark subareas, and when the mutation value is more, the concentric circle characteristics of the tool mark areas in the corresponding images are less obvious. In the embodiment of the invention, the convex hulls of the pixel points corresponding to the circle centers are obtained through a convex hull algorithm, and the areas of the convex hulls are calculated and recorded as
When the concentric circle characteristics of the tool marks on the image are more obvious, the positions of the corresponding circle centers are closer, and the inner area of the corresponding convex hulls is smaller. And taking the obtained Euclidean distance standard deviation between circle centers, the first mean value, the second mean value and the areas of the convex hulls as circle center distribution characteristics of the tool mark subareas. It should be noted that, the convex hull algorithm is well known in the art, and is not further defined and described herein.
Constructing a tool mark concentric circle saliency calculation model through the circle center distribution characteristics of the tool mark subregions of the drill bit and the number of the tool mark subregions of the drill bit to obtain corresponding concentric circle saliency, wherein the tool mark concentric circle saliency calculation model comprises:
wherein ,
is of significance of concentric circles->
For the first mean>
For the second mean>
Is the area of the convex hull, and the convex hull is the area of the convex hull,
for EuropeStandard deviation of distance>
For the number of bit tool mark subregions, +.>
For presetting the adjustment coefficient, < >>
The purpose of (2) is to prevent the denominator from being 0. In the embodiment of the present invention, < > a->
Set to 1.
The tool mark concentric circle saliency calculation model combines the position distribution characteristics of circle centers corresponding to all the drill bit tool mark subregions and the number of the drill bit tool mark subregions to jointly represent the tool mark concentric circle saliency, when the number of the drill bit tool mark subregions identified in the image is larger, the distance between circle centers corresponding to all the drill bit tool mark subregions is closer, and when the mutation value of the distance between the circle centers is smaller than the value difference of the mutation value which is not identified in the distances, the tool mark concentric circle saliency corresponding to the drill bit tool mark region in the image is larger
The larger the image, the more obvious the concentric circle feature of the tool mark corresponding to the image. The tool mark concentric circle saliency gives consideration to the number of the drill bit tool mark subregions and the distribution of the drill bit tool mark subregions corresponding to the circle centers of the fitting circles, so that the obtained tool mark concentric circle saliency is more accurate, and the concentric circle saliency characterizes the overall tool mark morphological characteristics of the face image.
Step S3: obtaining the cutter mark width of each position of the cutter mark subregion of the drill bit, detecting the quantity of corner points of the cutter mark subregion of the drill bit, and obtaining the cutter mark density according to the width distribution characteristics of the cutter mark width and the quantity of the corner points.
In order to enable the identification of the geological type to be more accurate, on the basis of obtaining the significance of the concentric circles corresponding to the drill bit tool mark subareas, the drill bit tool mark subareas in the image are analyzed in more detail. Because the tool marks are formed by the reciprocating impact chiseling of the drill bit, the forming reasons of different positions in the tool marks are the same, the formed characteristic textures are the same, and the widths of the tool marks at different positions on the communication domain corresponding to the same tool mark subarea are basically consistent; in addition, the number of corner points of the tool marks formed by geology with different densities is different; therefore, the geological type is further identified on the basis of the cutter mark density obtained through the cutter mark width distribution characteristics and the number of corner points corresponding to the cutter mark subareas.
In the embodiment of the invention, the center of each drill bit tool mark subarea is used as a basis for analysis, the center of each drill bit tool mark subarea is used as a starting point, rays are led out to all directions, the intersection of the rays and the drill bit tool mark subareas forms a line segment, the length corresponding to the line segment corresponds to a pixel point in the line segment, the length of the line segment is recorded as the tool mark width, namely, the tool mark width corresponding to the pixel point in the line segment is consistent, and the tool mark width in all directions is obtained according to the method. The number of rays is recorded as
Will->
The width of each tool mark is marked as->
, wherein />
The average value of these tool mark widths is marked as +.>
。
Preferably, a three-dimensional coordinate system is constructed according to the positions of pixel points in the drill bit tool mark sub-area and the tool mark widths corresponding to the pixel points, and the transverse axis of the image coordinate system is taken as the x axis of the three-dimensional coordinate system, and the longitudinal axis of the image coordinate systemAs the y-axis of the three-dimensional coordinate system, the width of the tool mark is taken as the z-axis of the three-dimensional coordinate system. Mapping each pixel point in the drill bit tool mark subarea to a three-dimensional coordinate system, in the embodiment of the invention, clustering the pixel points in the three-dimensional coordinate system by using 5 as the minimum inclusion point number and using 3 as the scanning radius through a DBSCAN algorithm to obtain more than two pixel point clustering sets, and recording the number of the pixel point clustering sets as
. It should be noted that the DBSCAN algorithm is well known in the art, and is not further defined and described herein.
Taking the difference between the tool mark width and the average value of the tool mark width and the number of pixel point clustering sets as the width distribution characteristics of the tool mark width, wherein the smaller the difference between the tool mark width and the average value in each direction of the tool mark subregion of the drill bit is, the more the pixel point clustering sets are, and the more the corresponding tool mark width is uniformly distributed in the tool mark subregion of the drill bit; conversely, the larger the difference between the width and the average value of the tool marks in each direction of the tool mark subarea of the drill bit, the fewer the pixel point clustering sets, and the more chaotic the corresponding tool mark widths are distributed in the tool mark subarea of the drill bit.
When the texture of the rock is tighter, the edges of the formed cutter mark subareas are clearer, more uniform and smoother, and the corner points are fewer; correspondingly, when the rock mass texture is loose, sand grains, gravel, clay and the like near the cutter mark are easy to agglomerate and fall off, the edge of the cutter mark is more tortuous and rough, and the corner points are more. Therefore, on the basis of obtaining the width distribution of the tool marks, the corner detection is carried out on each drill bit tool mark subarea, and the obtained number of the corner points is recorded as
. It should be noted that, the detection of the corner point is a technical means known to those skilled in the art, and will not be described herein.
Obtaining cutter mark density according to cutter mark width distribution characteristics, corner number and pixel clustering set through a cutter mark density model, wherein the cutter mark density model comprises:
wherein ,
is the density of the tool mark>
Is->
Width of each tool mark->
Is the average value of the width of the tool mark>
For the number of corner points +>
For the number of pixel cluster sets, +.>
Is the number of rays.
The tool mark density model characterizes tool mark characteristics of one of the drill bit tool mark subregions, specifically analyzes each drill bit tool mark subregion, combines the number of corner points in the drill bit tool mark subregion, the number of pixel point clustering sets and corresponding tool mark width distribution, and the product of the tool mark density and the number of corner points and the number of pixel point clustering sets is inversely proportional to the tool mark width distribution characteristics. The cutter mark density characterizes specific morphological characteristics of each drill bit cutter mark subarea, and the drill bit cutter mark subarea is analyzed in more detail, so that the identification of the geological type is more accurate.
Step S4: and obtaining stratum geological density according to the tool mark concentric circle significance and the tool mark density, and completing identification of geological types according to the stratum geological density.
According to the obtained tool mark concentric circle significance of the tool mark region of the drill bit
Tool mark density corresponding to each bit tool mark subregion>
Comprehensively evaluating the compaction degree of rock mass materials of the corresponding tunnel face of the image to construct stratum geological density +.>
. The construction of the stratum geological density according to the concentric circle significance and the tool mark density comprises the following steps:
wherein ,
is natural constant (18)>
For stratum geological density>
And the accumulated value of the tool mark density of all the drill bit tool mark subregions is obtained. Accumulating the tool mark density corresponding to each drill bit tool mark subregion to obtain a tool mark density accumulated value, mapping the obtained tool mark density accumulated value into an exponential function based on a natural constant, and taking the product of the mapped value of the tool mark density accumulated value and the significance of the tool mark concentric circles as stratum geological density.
Tool mark concentric circle significance of drill bit tool mark region
Characterizing the general character of the tool mark region, eachThe tool mark density of the drill bit tool mark subareas represents the characteristics of each drill bit tool mark subarea, namely the local characteristics of the tool mark subareas. The tool mark morphological characteristics are represented according to the combination of two parameters of the concentric circle saliency and the tool mark saliency, so that the whole tool mark morphological characteristics are considered, the part is included, and the geological type identification is more accurate.
Further, the geological type identification is completed according to the obtained stratum geological density, and the method is specific:
various geology includes but is not limited to hard rock stratum, broken bottom layer of hard rock, uneven hard and soft stratum, clay stratum, sand-containing water-rich stratum, and is manually classified and marked into three types of hard rock stratum, uneven hard and soft stratum and soft bottom layer. The stratum with stratum geological density greater than a first preset density threshold is divided into hard rock stratum, the stratum with stratum less than a second preset density threshold is divided into soft stratum, the stratum with stratum less than or equal to the first preset density threshold and greater than or equal to the second preset density threshold is divided into uneven soft and hard stratum, and the first preset density threshold is greater than the second preset density threshold, so that identification of geological types is completed.
In the embodiment of the invention, the stratum density corresponding to the hard rock stratum is obtained
The minimum value of (2) is marked +.>
The method comprises the steps of carrying out a first treatment on the surface of the Formation density corresponding to formation with uneven hardness>
Maximum value is marked as->
，/>
The minimum value is marked->
The method comprises the steps of carrying out a first treatment on the surface of the Stratum geological density corresponding to soft stratum +.>
Maximum value is marked as->
. Marking the first preset density threshold value as +.>
The second preset density threshold is marked +.>
. Wherein the first preset density threshold +.>
Formation compactness corresponding to hard rock formation>
Minimum value +.>
Formation density corresponding to formation with uneven hardness ∈>
Maximum value of>
Expressed as the mean value of->
. A second preset density threshold +.>
Formation density corresponding to formation with uneven hardness>
Minimum value +.>
Stratum geological density corresponding to soft stratum +.>
Maximum value of>
Expressed as the mean value of->
。
In summary, according to the invention, by collecting the tool mark image data formed on the rock body by the drill bit in the working process of the rock breaker, the concentric circle significance and the tool mark compactness are obtained according to the collected tool mark image data, the stratum geological compactness is further represented by the concentric circle significance and the tool mark compactness, and the identification of the geological type is completed according to the stratum geological compactness. According to the invention, the overall characteristics of the tool mark image are represented according to the significance of the concentric circles, the local characteristics of the tool mark image are represented according to the density of the tool marks, and the identification of the geological type is accurately completed by combining the whole with the local, and the geological type is identified according to the tool mark image formed on the rock body by the drill bit, so that the cost is lower compared with the prior art. Therefore, the invention has lower cost while ensuring the accuracy.
It should be noted that: the sequence of the embodiments of the present invention is only for description, and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments.
The foregoing description of the preferred embodiments of the invention is not intended to limit the invention to the precise form disclosed, and any such modifications, equivalents, and alternatives falling within the spirit and scope of the invention are intended to be included within the scope of the invention.
Claims (6)
1. A method of geological type identification, the method comprising:
acquiring a denoised face image generated by tunneling of a rock breaker, taking a part of the face image, the gray value of which is larger than a preset first threshold value, as a first screening area, wherein the first screening area comprises a plurality of connected areas, and screening out drill bit tool mark subareas of the connected areas according to the fitting degree of the connected areas and circles;
obtaining a circle center of a corresponding drill bit tool mark subarea according to the fitting circle corresponding to each drill bit tool mark subarea, and obtaining a tool mark concentric circle significance according to the position distribution characteristics among the circle centers of the drill bit tool mark subareas and the number of the drill bit tool mark subareas;
obtaining the width of the cutter mark at each position of the cutter mark subregion of the drill bit, detecting the quantity of corner points of the cutter mark subregion of the drill bit, and obtaining the density of the cutter mark according to the width distribution characteristics of the width of the cutter mark and the quantity of the corner points;
obtaining stratum geological density according to the tool mark concentric circle significance and the tool mark density, and completing identification of geological types according to the stratum geological density;
the obtaining the width of the tool mark at each position of the tool mark subarea of the drill bit comprises the following steps:
taking the circle center of a fitting circle corresponding to the drill bit tool mark subarea as a starting point, obtaining rays in all directions, and taking the length of a line segment of the rays in the edge of the drill bit tool mark subarea as the tool mark width;
the width distribution feature of the tool mark width comprises:
constructing a three-dimensional coordinate system based on the positions of pixel points in the drill bit tool mark sub-area and the tool mark widths corresponding to the pixel points, wherein the x-axis of the three-dimensional coordinate system is the transverse axis of an image coordinate system, the y-axis is the longitudinal axis of the image coordinate system, and the z-axis is the tool mark width; mapping each pixel point in the drill bit tool mark subarea to the three-dimensional coordinate system; clustering pixel points in the three-dimensional coordinate system by a clustering algorithm in the three-dimensional coordinate system to obtain a pixel point clustering set; taking the difference between the width of each tool mark and the average value of the width of the tool mark and the number of the pixel point clustering sets as the width distribution characteristics of the width of the tool mark;
the obtaining the cutter mark density according to the width distribution characteristics of the cutter mark width and the number of corner points comprises the following steps:
cutter mark density is obtained through a cutter mark density model according to cutter mark width distribution characteristics, corner number and pixel clustering set, and the cutter mark density model comprises:
；
wherein ,
for the compactness of the tool mark, +.>
Is->
Width of each tool mark->
As the average value of the width of the tool mark,
for the number of corner points +.>
For the number of clusters of pixels, < >>
Is the number of rays;
the obtaining the stratum geological density according to the tool mark concentric circle significance and the tool mark density comprises the following steps:
accumulating the tool mark density to obtain a tool mark density accumulated value, mapping the tool mark density accumulated value into an exponential function based on a natural constant, and taking the product of the exponential function and the corresponding concentric circle significance as the stratum geological density.
2. The method for identifying a geologic type according to claim 1, wherein the method for obtaining the location distribution feature comprises:
calculating Euclidean distances between circle centers of the cutter mark subregions of each drill bit, calculating standard deviation of the Euclidean distances, and screening mutation values through a BG segmentation algorithm after the Euclidean distances are arranged from small to large; calculating a first mean value of the mutation value and screening a second mean value corresponding to other Euclidean distances except the mutation value, and obtaining a convex hull formed by circle centers of the drill bit tool mark subregions according to a convex hull algorithm to obtain the area of the convex hull; if the mutation value does not exist, the first average value and the second average value are equal;
and taking the standard deviation, the first mean value, the second mean value and the area of the convex hull as the position distribution characteristics.
3. The geological type identification method according to claim 2, wherein obtaining the significance of the concentric circles of the tool marks according to the position distribution characteristics between the circle centers of the tool mark sub-areas of the drill bit and the number of the tool mark sub-areas of the drill bit comprises:
obtaining the tool mark concentric circle saliency through a tool mark concentric circle saliency calculation model according to the position distribution characteristics among the circle centers of the tool mark subregions of the drill bit and the number of the tool mark subregions of the drill bit, wherein the tool mark concentric circle saliency calculation model comprises:
；
wherein ,
for the significance of the concentric circles of the tool marks, +.>
For said first mean,/a>
For said second mean,/>
For the area of the convex hull, +.>
For the standard deviation of the Euclidean distance, < >>
For the number of bit tool mark subregions, < >>
Is a preset adjustment coefficient.
4. A method of geological type identification according to claim 1, wherein said completing identification of geological type from said formation geological density comprises:
the stratum with stratum geological density larger than a first preset density threshold is divided into hard rock stratum, the stratum with stratum smaller than a second preset density threshold is divided into soft stratum, the stratum with stratum smaller than or equal to the first preset density threshold and larger than or equal to the second preset density threshold is divided into uneven soft and hard stratum, and the first preset density threshold is larger than the second preset density threshold.
5. The geological type identification method of claim 1, wherein the screening the drill bit tool mark subregion of the connected domain according to the fitting degree of the connected domain and the circle comprises:
and marking the region where the connected domain corresponding to the circle fitting degree larger than the preset fitting degree threshold value is located as a drill bit tool mark sub-region.
6. The geological type identification method of claim 1, wherein said connected domain acquisition method in said first screening area comprises:
and carrying out cluster analysis on the pixel points contained in the first screening area by using a spectral clustering algorithm to obtain a plurality of connected areas.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211563539.9A CN115661133B (en) | 2022-12-07 | 2022-12-07 | Geological type identification method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211563539.9A CN115661133B (en) | 2022-12-07 | 2022-12-07 | Geological type identification method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115661133A CN115661133A (en) | 2023-01-31 |
| CN115661133B true CN115661133B (en) | 2023-05-23 |
Family
ID=85019765
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211563539.9A Active CN115661133B (en) | 2022-12-07 | 2022-12-07 | Geological type identification method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115661133B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022100609A1 (en) * | 2020-11-11 | 2022-05-19 | 上海中联重科桩工机械有限公司 | Geological hardness identification method and system for engineering machinery |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2031423B1 (en) * | 2007-08-31 | 2013-05-15 | Services Pétroliers Schlumberger | Identifying geological features in an image of an underground formation surrounding a borehole |
| WO2011094817A1 (en) * | 2010-02-05 | 2011-08-11 | The University Of Sydney | Rock property measurements while drilling |
| CN106225770B (en) * | 2016-08-26 | 2018-12-25 | 招商局重庆交通科研设计院有限公司 | The multidimensional digitized record recognition methods of tunnel tunnel face geology and system |
| CN112990227B (en) * | 2021-02-08 | 2022-12-27 | 中国铁建重工集团股份有限公司 | Face geology detection method |
-
2022
- 2022-12-07 CN CN202211563539.9A patent/CN115661133B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022100609A1 (en) * | 2020-11-11 | 2022-05-19 | 上海中联重科桩工机械有限公司 | Geological hardness identification method and system for engineering machinery |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115661133A (en) | 2023-01-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP2031423B1 (en) | Identifying geological features in an image of an underground formation surrounding a borehole | |
| US11530998B2 (en) | Method and system to analyze geologic formation properties | |
| CN107133630B (en) | Method for judging carbonate rock pore type based on scanned image | |
| WO2017114443A1 (en) | Method and device for determining dissolution degree of karst reservoir | |
| CN107273608A (en) | A kind of reservoir geology profile vectorization method | |
| CN110287884A (en) | A kind of auxiliary drive in crimping detection method | |
| CN112396612B (en) | Vector information assisted remote sensing image road information automatic extraction method | |
| CN1198217A (en) | Method for automatically determining stratification beds in a site | |
| CN117710399B (en) | Crack contour extraction method in geological survey based on vision | |
| CN116912256B (en) | Corrugated paper rib defect degree assessment method based on image processing | |
| CN115082436B (en) | Shield tunneling machine tool bit production defect detection method | |
| Delhomme | A quantitative characterization of formation heterogeneities based on borehole image analysis | |
| CN115661133B (en) | Geological type identification method | |
| CN114241372A (en) | Target identification method applied to sector-scan splicing | |
| CN106014397A (en) | Imaging logging fractured-cavern reservoir parameter extracting method | |
| CN106296678A (en) | RQD based on boring optical image technology analyzes method | |
| CN111951347B (en) | Shale oil and gas reservoir sandy texture parameter extraction method | |
| CN111091049B (en) | Road surface obstacle detection method based on reverse feature matching | |
| CN112963160A (en) | Method for identifying and determining stratum characteristics by using shield real-time tunneling parameters | |
| CN115758038B (en) | Stratum composite ratio calculation method, device, equipment and medium for shield construction | |
| CN109472867B (en) | Method for quantifying influence range of drilling position information | |
| CN115640546A (en) | Lithology identification method based on fusion of image and feature information | |
| Kherroubi | Automatic extraction of natural fracture traces from borehole images | |
| CN108828687A (en) | A kind of calculation of permeability based on Electrical imaging Areal porosity | |
| Noufal et al. | Carbonate Reservoir Permeability Estimation from Borehole Image Logs |
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 |