Geological information efficient extraction and calculation method based on tunnel engineering geological longitudinal profile drawing

Abstract

The invention discloses a geological information efficient extraction and calculation method based on a tunnel engineering geological longitudinal profile drawing, and relates to the technical field of geological information extraction and calculation of a geological longitudinal profile drawing, and the method comprises the following steps: S1, filling a tunnel geological longitudinal profile CAD drawing; s2, converting the geological longitudinal section CAD drawing into an image format; s3, image filling and tunnel axis position extraction; s4, tunnel axis removal and tunnel excavation face stratum extraction; s5, the stratum proportion of the tunnel excavation face range is calculated; s6, performing stratum type identification and thickness calculation in the mileage direction of the tunnel; the method has the advantages that on the basis of the geological profile diagram, design parameters such as an engineering geological survey report and the tunnel excavation diameter are considered, geological information of the tunnel crossing area is rapidly extracted and calculated, and foundation support is provided for shield design, site construction and data mining.

Description

Technical Field

[0001] The present invention relates to the technical field of geological information extraction of geological longitudinal profiles, and in particular to a method for efficiently extracting and calculating geological information based on a tunnel engineering geological longitudinal profile. Background Art

[0002] The geological information of the geological longitudinal profile in the construction of tunnel engineering plays an important guiding role in the construction. Combined with the geological survey report, it can obtain the types of strata involved in the tunnel line, physical and mechanical properties, etc. to a large extent, as an important basis for construction decision-making. Especially in the construction of shield tunnels, many links such as shield equipment selection, construction method preparation and implementation rely on geological information, especially the application of shield intelligent excavation, intelligent construction and big data technology, which requires a large amount of information to be extracted from CAD geological longitudinal profiles, which is difficult for manual operation. Therefore, it is necessary to automatically extract information from CAD geological longitudinal profiles in batches. Generally, it can be achieved through CAD secondary development technology, but it requires the construction of a professional development environment and familiarity with dedicated interfaces. It is difficult and inefficient, and it is difficult for general engineering and technical personnel to achieve. Therefore, a method for extracting geological information from geological longitudinal profiles that is simpler to operate and more efficient is needed. Summary of the invention

[0003] The purpose of the present invention is to provide a method for efficiently extracting and calculating geological information based on the geological longitudinal profile of tunnel engineering in order to solve the above-mentioned problems. The method has strong operability, high calculation accuracy and high calculation efficiency, and has a wide range of application prospects. It is particularly suitable for the rapid extraction of geological information from geological longitudinal profiles involved in shield tunnel construction.

[0004] The present invention achieves the above-mentioned purpose through the following technical solutions:

[0005] A method for efficiently extracting and calculating geological information based on a tunnel engineering geological longitudinal profile includes the following steps:

[0006] S1: Filling the tunnel geological longitudinal section CAD drawing, filling the strata in the tunnel geological longitudinal section CAD drawing that are not filled with a single color with a solid color, requiring that each solid color corresponds to a single stratum;

[0007] S2: convert the geological longitudinal section CAD drawing into an image format, select the window range in the CAD drawing, use the print function to convert the tunnel geological longitudinal section interval into an image format recorded as img1, and record the horizontal length and vertical height of the geological longitudinal section;

[0008] S3: Image filling and tunnel axis position extraction, using image processing software to keep the original color of the tunnel axis position in image img1 unchanged, and fill the area outside the axis position with other single colors to form image img2, and use programming to use the colors of different pixel positions to determine whether it is the tunnel axis, and then extract the tunnel axis position;

[0009] S4: Tunnel axis removal and tunnel excavation surface stratum extraction, process the image img1, adjust the color matrix corresponding to the pixel points at the axis position to the color matrix of the pixel points in the adjacent area on the axis, remove the tunnel axis to form img3, use the k-means algorithm to perform color clustering on the image img3, convert the colors with slight color differences into a single color, and finally achieve the purpose of each stratum corresponding to one color, determine the upper and lower limits of the tunnel height at different mileage positions through the position of the pixel points on the tunnel axis and the size of the tunnel excavation, read the color matrix of the pixel points between the upper and lower limits to determine the type of excavation surface stratum, and realize the extraction of the tunnel excavation surface stratum;

[0010] S5: Calculate the proportion of the strata in the tunnel excavation surface, starting from each pixel position at the upper limit of the tunnel range in the horizontal direction, scan in the vertical direction, calculate the number of pixels occupied by each stratum in the vertical direction one by one, and finally calculate the proportion of each stratum in the excavation surface range according to the thickness of each stratum;

[0011] S6: Identification of stratum types and calculation of thickness along the mileage direction of the tunnel. For each pixel position in the horizontal direction, calculation is started from the upper limit of the height, and scanning is performed in the vertical direction. The stratum type is determined by the color matrix at the pixel point, and the number of pixels occupied by each stratum in the vertical direction is calculated one by one. The vertical length of each stratum is obtained by dividing the total number of pixels in the vertical direction by the actual vertical height corresponding to the address longitudinal section diagram, and the thickness of each stratum is obtained by multiplying the number of pixels in the vertical direction of each stratum by the vertical length of each pixel; similarly, the horizontal length of each stratum is obtained by dividing the total number of pixels in the horizontal direction by the actual horizontal length corresponding to the address longitudinal section diagram, and the corresponding mileage is obtained by multiplying the number of pixels in the horizontal direction of each stratum by the horizontal length of each pixel.

[0012] Preferably: in the process of changing the cross-section filling color of the CAD drawing in S1, the pattern filling legend corresponding to each layer is changed synchronously.

[0013] Preferably, the horizontal length and vertical height of the geological longitudinal section recorded in S2 are represented as corresponding actual lengths or heights.

[0014] Preferably: when extracting the tunnel axis position in S3, the image is read using image processing software to obtain the image width and height, wherein the image width corresponds to the horizontal direction of the geological longitudinal profile, the image height corresponds to the vertical direction of the geological longitudinal profile, the starting position is the upper left corner of the image, and by judging whether the color matrix of each pixel point is filled with a single color, it is determined whether the position is the tunnel axis position, and a set of pixel point positions on the tunnel axis is obtained.

[0015] Preferably: when the k-means algorithm is used in S4 to perform color clustering on the image, the RGB values ​​of k colors in the image are randomly selected as the centroids, the distance between the RGB value of each remaining pixel point in the image and the k centroids is calculated, and it is assigned to the class of the nearest centroid, and the centroids of each class that has been obtained are recalculated, and iterated until the new centroid is equal to the original centroid or less than a specified threshold.

[0016] Preferably: when determining the upper and lower limits of the tunnel height at different mileage positions in S4, the upper and lower limits of the vertical pixel position are calculated based on the obtained pixel point position set on the tunnel axis, and the upper and lower limits of the tunnel excavation surface range are calculated according to the tunnel excavation diameter and the unit pixel length, and the type of excavation surface stratum is determined by reading the color matrix of the pixel points between the upper and lower limit positions.

[0017] Preferably, in S5, the stratum ratio within the tunnel excavation surface is calculated based on the area occupied by each stratum within the excavation surface and the number of stratum layers.

[0018] Preferably: when identifying the type of strata and calculating the thickness along the mileage direction of the tunnel in S6, the type of strata and the thickness calculation are performed between the highest position and the lowest position in the geological longitudinal section, and the stratum thickness and the corresponding mileage are calculated based on the unit pixel length.

[0019] Compared with the prior art, the invention has the following beneficial effects: by converting the CAD image into a picture format, and then using a clustering algorithm to obtain a geological longitudinal section filled with pure colors, the color matrix in the image can correspond to the corresponding strata and stratum parameters, thus realizing the mapping of image colors to geological information. By relying on subsequent computer image processing to extract geological information of the geological longitudinal section, the invention has the characteristics of strong operability, fast extraction efficiency and high precision, and provides reliable geological data support for intelligent excavation, intelligent tunnel construction, etc. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0021] Figure 1 This is a flowchart of Example 1 of the present invention.

[0022] Figure 2 is the image img1.

[0023] Figure 3 is the image img2.

[0024] Figure 4 is the image img3.

[0025] Figure 5 This is the result map of the pixel position extraction of the tunnel axis. DETAILED DESCRIPTION

[0026] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0027] Example 1

[0028] like Figure 1 As shown, a method for efficiently extracting and calculating geological information based on a tunnel engineering geological longitudinal profile includes the following steps:

[0029] S1: Filling the tunnel geological longitudinal section CAD drawing; filling the strata filled with non-single colors (including gradient colors, patterns, etc.) in the tunnel geological longitudinal section CAD drawing with solid colors, requiring each solid color to correspond to a single stratum, so as to facilitate the subsequent identification of the strata according to the difference in color; at the same time, in the process of changing the section filling color of the CAD drawing, the pattern filling legend corresponding to each stratum is changed synchronously to facilitate the subsequent comparison;

[0030] S2: Convert the geological longitudinal section CAD image into image format; select the window range in the CAD image, use the print function to select the tunnel geological longitudinal section interval and convert it into image format and record it as image img1 (see Figure 2 As shown), the length L of the geological longitudinal section in the horizontal direction is recorded at the same time. x is 3047.50m and the vertical height L y is 54.3140m; Lx and Ly represent the actual length or height corresponding to the horizontal and vertical directions;

[0031] S3: Image filling and tunnel axis position extraction; using image processing software such as Photoshop, the original color of the tunnel axis position in the image img1 is kept unchanged, and the area outside the axis position is filled with other single color C1 (different from the color of the tunnel axis position, white RGB (255,255,255) in this embodiment) to form image img2 (see Figure 3As shown); Since the image color generated by the printing function has a certain color difference, the red RGB in the image is not all (255,0,0), and the color filled by photoshop is a single color C1, the color of different pixel positions can be used to determine whether it is the tunnel axis through programming. The judgment logic here is that the pixel color matrix is ​​not RGB (255,255,255), so the point can be judged as a point on the tunnel axis, and then the tunnel axis position can be extracted;

[0032] S4: Tunnel axis removal and tunnel excavation surface stratum extraction; To process the image img1, it is necessary to adjust the color matrix corresponding to the pixel points at the axis position to the color matrix of the pixel points in the adjacent area on the axis, so as to remove the tunnel axis and form the image img3; Use the k-means algorithm to perform color clustering on img3 to convert the colors with slight color differences in the image img3 into a single color, and finally achieve the purpose of corresponding one color to each stratum. The processed image is as follows Figure 4 As shown; through the location of the pixel points on the tunnel axis and the size of the tunnel excavation (the result is shown in Figure 5 As shown in the figure, determine the upper and lower limits of the tunnel height at different mileage positions; determine the type of excavation surface stratum by reading the color matrix of the pixel points between the upper and lower limit positions, and realize the extraction of tunnel excavation surface stratum;

[0033] S5: Calculation of the proportion of strata within the tunnel excavation surface; starting from each pixel position at the upper limit of the tunnel range in the horizontal direction, scanning in the vertical direction, calculating the number of pixels occupied by each stratum in the vertical direction (the thickness of each stratum within the tunnel excavation surface) one by one, and finally calculating the proportion of each stratum within the excavation surface range based on the thickness of each stratum within the tunnel excavation surface range;

[0034] S6: Identification of stratum types and thickness calculation along the mileage direction of the tunnel; for each pixel point in the horizontal direction, calculation is started from the upper limit of the height, and scanning is performed in the vertical direction. First, the stratum type is determined by the color matrix at the pixel point, and the number of pixels occupied by each stratum in the vertical direction is calculated one by one, L px is the vertical length of the unit pixel, L v (451 in this embodiment) is the total number of pixels in the vertical direction, where L px =L y / L v , the number of pixels in the vertical direction of each stratum multiplied by L px The thickness of the stratum can be calculated; L py is the horizontal length of the unit pixel, L h (4961 in this embodiment) is the total number of pixels in the horizontal direction, where L py =L h / L h; Mileage conversion is calculated by multiplying the number of pixels in the horizontal direction by L py The corresponding mileage can be calculated;

[0035] In this embodiment, the image img2 generated in S3 is read by a program compiled by, but not limited to, matlab software to obtain the image width (in pixels) and height (in pixels), wherein the image width corresponds to the horizontal direction of the geological longitudinal profile, the image height corresponds to the vertical direction of the geological longitudinal profile, and the starting position is the upper left corner of the image; the tunnel axis position extraction includes: ① calculating the number of pixels M in the width direction and calculating the number of pixels N in the height direction; ② i takes integers from 1 to M, and j starts to take values ​​from 1. If the color represented by the color matrix at the pixel point (i, j) is not C1, then the position indicates that the vertical position corresponding to the tunnel axis at the pixel point i in the horizontal direction is at the pixel point j, and the position of the tunnel axis at the pixel point i in the horizontal direction is extracted; ③ if the color represented by the color matrix at the pixel point (i, j) is C1, j=j+1, repeat ②; until the vertical positions of the tunnel axes corresponding to the pixels 1 to M in the horizontal direction are all calculated, and L px , L py And the pixel position on the tunnel axis completes the tunnel axis position extraction.

[0036] In this embodiment, S4 uses the k-means algorithm to cluster the colors in img3, including the following steps: ① randomly select the RGB values ​​of k colors in img3 as the centroid, k is the number of stratum types; ② calculate the distance between the RGB value of each remaining pixel point in the image and the k centroids, and assign it to the class of the nearest centroid; ③ recalculate the centroids of each class that has been obtained; ④ iterate steps ②-③ until the new centroid is equal to or less than the specified threshold value, and the solution is completed; the k clusters finally obtained are mapped to the stratum, and a unified RGB value is assigned to each category to obtain a stratum labeled image; in addition, the upper and lower limits of the tunnel height at different mileage positions of the tunnel are determined, including the following steps: ① based on the obtained pixel point position set on the tunnel axis, the upper and lower limits of the vertical pixel point position are calculated, R is the tunnel excavation B radius, and R / L is calculated. py And round it off to the nearest integer and record it as Round(R / L py );②Assume that the vertical pixel position of a pixel point on the axis of a tunnel is S py , the upper limit of the tunnel excavation surface range corresponding to this location is S py +Round(R / L py ), the lower limit of the tunnel excavation surface is S py -Round(R / L py );③Bi takes integers from 1 to M (M is the number of pixels in the width direction M), j is from S py -Round(R / Lpy ) starts to fetch values, read (B i , S py -Round(R / L py )) color matrix, according to the determination of the stratum type, the stratum height is recorded as 1 pixel, and the vertical pixel coordinate is added by 1 on the original basis and recorded as C jj ④Read(B i , C jj ) color matrix, if the color matrix is ​​the same as (B i , C jj -1) color matrix is ​​consistent, the number of pixels of the formation height is increased by 1 on the original basis, C jj =C jj +1; if the color matrix is ​​the same as (B i , C jj -1) color matrix is ​​inconsistent, read (B i , C jj ) color matrix, according to the determination of the stratum type, the stratum height is recorded as 1 pixel, C jj =C jj +1; ⑤Repeat step ④, C jj >S py +Round(R / L py ) exit the loop; the total number of strata within the excavation surface, the number of pixels occupied by each stratum in the numerical direction, and the coordinate values ​​of the starting pixel points and the ending pixel points in the vertical direction of each stratum can be obtained; the stratum thickness can be calculated according to the number of pixels occupied by each stratum in the numerical direction and L py Just multiply them to get the answer.

[0037] In this embodiment, the stratum ratio within the tunnel excavation surface in S5 is calculated by referring to formula (1) and formula (2):

[0038]

[0039] In formula (1), S i is the proportion of stratum i in the excavation surface, A i is the area occupied by stratum i in the excavation surface, N is the number of strata; in formula (2), h di 、h ui are the coordinate values ​​of the ending pixel point and the starting pixel point of stratum i in the vertical direction; D is the tunnel excavation diameter.

[0040] The stratum type identification and thickness calculation along the mileage direction of the tunnel in S6 are carried out between the highest position and the lowest position in the geological longitudinal section. The characteristics of the operation steps are as follows: ①B i Take an integer from 1 to M (M is the number of pixels in the width direction), j starts at 1, and reads (B i, 1) color matrix, according to the determination of the stratum type, the stratum height is recorded as 1 pixel, and the vertical pixel coordinate is added by 1 on the original basis and recorded as C jj ④Read(B i , C jj ) color matrix, if the color matrix is ​​the same as (B i , C jj -1) color matrix is ​​consistent, the number of pixels of the formation height is increased by 1 on the original basis, C jj =C jj +1; if the color matrix is ​​the same as (B i , C jj -1) color matrix is ​​inconsistent, read (B i , C jj ) color matrix, according to the determination of the stratum type, the stratum height is recorded as 1 pixel, C jj =C jj +1; ⑤Repeat step ④, C jj > N (number of pixels in height direction N) to exit the loop; the type and thickness of the strata along the mileage direction of the tunnel, the number of pixels occupied by each stratum in the vertical direction, and the coordinate values ​​of the starting pixel point and the ending pixel point in the vertical direction of each stratum can be obtained; the stratum thickness can be calculated according to the number of pixels occupied by each stratum in the vertical direction and L py Multiply to get

[0041] The basic principles, main features and advantages of the present invention are shown and described above. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions are only for illustrating the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, and these changes and improvements all fall within the scope of the present invention to be protected.

Claims

1. A method for efficiently extracting and calculating geological information based on a tunnel engineering geological longitudinal profile, characterized in that: The following steps are involved: S1: Filling the tunnel geological longitudinal section CAD drawing, filling the strata in the tunnel geological longitudinal section CAD drawing that are not filled with a single color with a solid color, requiring that each solid color corresponds to a single stratum; S2: convert the geological longitudinal section CAD drawing into an image format, select the window range in the CAD drawing, use the print function to convert the tunnel geological longitudinal section interval into an image format recorded as img1, and record the horizontal length and vertical height of the geological longitudinal section; S3: Image filling and tunnel axis position extraction, using image processing software to keep the original color of the tunnel axis position in image img1 unchanged, and fill the area outside the axis position with other single colors to form image img2, and use programming to use the colors of different pixel positions to determine whether it is the tunnel axis, and then extract the tunnel axis position; S4: Tunnel axis removal and tunnel excavation surface stratum extraction, process the image img1, adjust the color matrix corresponding to the pixel points at the axis position to the color matrix of the pixel points in the adjacent area on the axis, remove the tunnel axis to form img3, use the k-means algorithm to perform color clustering on the image img3, convert the colors with slight color differences into a single color, and finally achieve the purpose of each stratum corresponding to one color, determine the upper and lower limits of the tunnel height at different mileage positions through the position of the pixel points on the tunnel axis and the size of the tunnel excavation, read the color matrix of the pixel points between the upper and lower limits to determine the type of excavation surface stratum, and realize the extraction of the tunnel excavation surface stratum; S5: Calculate the proportion of the strata in the tunnel excavation surface, starting from each pixel position at the upper limit of the tunnel range in the horizontal direction, scan in the vertical direction, calculate the number of pixels occupied by each stratum in the vertical direction one by one, and finally calculate the proportion of each stratum in the excavation surface range according to the thickness of each stratum; S6: The tunnel carries out stratum type identification and thickness calculation along the mileage direction, calculates several vertical positions corresponding to each pixel in the horizontal direction, starts from the upper limit of the height, scans in the vertical direction, determines the stratum type by the color matrix at the pixel point, calculates the number of pixels occupied by each stratum in the vertical direction one by one, and divides the total number of pixels in the vertical direction by the actual vertical height corresponding to the address longitudinal section diagram to obtain the vertical length per pixel, and multiplies the number of pixels in the vertical direction of each stratum by the vertical length per pixel to obtain the thickness of each stratum; similarly, divides the total number of pixels in the horizontal direction by the actual horizontal length corresponding to the address longitudinal section diagram to obtain the horizontal length per pixel, and multiplies the number of pixels in the horizontal direction of each stratum by the horizontal length per pixel to obtain the corresponding mileage.

2. The method for efficiently extracting and calculating geological information based on a tunnel engineering geological longitudinal profile according to claim 1, characterized in that: In S1, when changing the section fill color of the CAD drawing, the drawing fill legend corresponding to each layer is changed synchronously.

3. The method for efficiently extracting and calculating geological information based on a tunnel engineering geological longitudinal profile according to claim 1, characterized in that: The horizontal length and vertical height of the geological longitudinal section recorded in S2 are expressed as the corresponding actual length or height.

4. The method for efficiently extracting and calculating geological information based on a tunnel engineering geological longitudinal profile according to claim 1, characterized in that: When extracting the tunnel axis position in S3, the image processing software is used to read the image and obtain the image width and height, where the image width corresponds to the horizontal direction of the geological longitudinal profile, and the image height corresponds to the vertical direction of the geological longitudinal profile. The starting position is the upper left corner of the image. By judging whether the color matrix of each pixel point is filled with a single color, it is determined whether the position is the tunnel axis position, and the pixel point position set on the tunnel axis is obtained.

5. The method for efficiently extracting and calculating geological information based on a tunnel engineering geological longitudinal profile according to claim 1, characterized in that: When using the k-means algorithm to perform color clustering on an image in S4, it involves randomly selecting the RGB values ​​of k colors in the image as the centroids, calculating the distance between the RGB values ​​of each remaining pixel in the image and the k centroids, and assigning them to the class of the nearest centroid, recalculating the centroids of each class that has been obtained, and iterating until the new centroid is equal to the original centroid or less than the specified threshold.

6. The method for efficiently extracting and calculating geological information based on a tunnel engineering geological longitudinal profile according to claim 4, characterized in that: When determining the upper and lower limits of the tunnel height at different mileage positions in S4, the upper and lower limits of the vertical pixel position are calculated based on the obtained pixel point position set on the tunnel axis, and the upper and lower limits of the tunnel excavation surface range are calculated according to the tunnel excavation diameter and the unit pixel length. The type of excavation surface stratum is determined by reading the color matrix of the pixel points between the upper and lower limit positions.

7. The method for efficiently extracting and calculating geological information based on a tunnel engineering geological longitudinal profile according to claim 1, characterized in that: The calculation of the stratum ratio within the tunnel excavation surface in S5 is based on the area occupied by each stratum within the excavation surface and the number of stratum layers.

8. The method for efficiently extracting and calculating geological information based on a tunnel engineering geological longitudinal profile according to claim 1, characterized in that: When identifying the type of strata and calculating the thickness along the mileage direction of the S6 tunnel, the strata type is identified and the thickness is calculated between the highest and lowest positions in the geological longitudinal section, and the stratum thickness and the corresponding mileage are calculated based on the unit pixel length.

Images