A method for efficient extraction and calculation of geological information based on tunnel engineering geological longitudinal section

Abstract

The application discloses a kind of based on tunnel engineering geology longitudinal section map geological information efficient extraction and calculation method, it is related to geological information extraction and calculation technical field of geological longitudinal section map, including the following steps: S1: tunnel geology longitudinal section CAD map filling;S2: geological longitudinal section CAD map is converted into image format;S3: image filling and tunnel axis position extraction;S4: tunnel axis removal and tunnel excavation surface stratum extraction;S5: tunnel excavation surface range stratum proportion calculation;S6: tunnel along mileage direction stratum kind identification and thickness calculation;Beneficial effect lies in: the present application is based on geological longitudinal section map, considers engineering geological survey report and tunnel excavation diameter etc. Design parameter, quickly extract the geological information of tunnel crossing area and calculate, provide basic support for shield design, field construction and data mining.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of geological information extraction of geological longitudinal section, and particularly relates to a geological information efficient extraction and calculation method based on a tunnel engineering geological longitudinal section. BACKGROUND

[0002] The geological information of the geological longitudinal section in tunnel engineering construction has an important guiding effect on construction, and in combination with a geological survey report, the types of strata and physical and mechanical properties involved in the tunnel line can be obtained to a great extent as an important basis for construction decision. In particular, in the construction of a shield tunnel, the selection of shield equipment, the preparation and implementation of construction methods and other aspects depend on geological information, especially the application of intelligent tunneling, intelligent construction and big data technology, which requires a large amount of information to be extracted from CAD geological longitudinal sections, which is difficult for manual operation, so it is necessary to automatically extract information from CAD geological longitudinal sections in batches. Generally, it can be realized through CAD secondary development technology, but it needs to build a professional development environment and be familiar with special interfaces, which is difficult and inefficient, and is difficult for general engineering and technical personnel to realize. Therefore, a geological information extraction method for geological longitudinal sections is needed, which is more simple to operate and more efficient. SUMMARY

[0003] The purpose of the present application is to provide a geological information efficient extraction and calculation method based on a tunnel engineering geological longitudinal section to solve the above problems, which has strong operability, high calculation precision and high calculation efficiency, has a wide application prospect, and is especially suitable for fast extraction of geological information of geological longitudinal sections involved in shield tunnel construction.

[0004] The present application achieves the above-mentioned purposes through the following technical solutions:

[0005] A geological information efficient extraction and calculation method based on a tunnel engineering geological longitudinal section, comprising the following steps:

[0006] S1: tunnel geological longitudinal section CAD filling, filling the stratum in the tunnel geological longitudinal section CAD with non-single color according to pure color, requiring that each pure color corresponds to a single stratum;

[0007] S2: converting the geological longitudinal section CAD into an image format, selecting a window range in the CAD, using the printing function to convert the tunnel geological longitudinal section interval into an image format img1, and recording the length in the horizontal direction and the height in the vertical direction of the geological longitudinal section;

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

[0009] S4: Tunnel axis removal and tunnel excavation surface stratum extraction, processing the image img1, adjusting the color matrix of the pixel points corresponding to the axis position to the color matrix of the pixel points in the adjacent area of the axis, removing the tunnel axis to form img3, using k-means algorithm for color clustering of the image img3, converting the color with slight color difference into single color, finally achieving the purpose of corresponding one color for each stratum, determining the upper limit and lower limit of the tunnel height at different mileage positions of the tunnel through the pixel point position of the tunnel axis and the size of the tunnel excavation, reading the color matrix of the pixel points between the upper and lower limit positions to determine the stratum type of the excavation surface, and realizing the extraction of the tunnel excavation surface stratum;

[0010] S5: Tunnel excavation surface range stratum proportion calculation, starting from each pixel point position at the upper limit of the tunnel range height along the horizontal direction, scanning along the vertical direction, calculating the number of pixel points occupied by each stratum in the vertical direction one by one, and finally calculating the proportion of each stratum in the excavation surface range according to the thickness of each stratum;

[0011] S6: Tunnel along mileage direction stratum type identification and thickness calculation, starting from the upper limit of the height at each pixel point position in the horizontal direction, scanning along the vertical direction, judging the stratum type through the color matrix of the pixel point, calculating the number of pixel points occupied by each stratum in the vertical direction one by one, and according to the total number of pixel points in the vertical direction, dividing the actual vertical height corresponding to the address longitudinal section to obtain the length of the vertical direction per pixel, and multiplying the thickness of each stratum by the length of the vertical direction per pixel to obtain the thickness of each stratum; Similarly, according to the total number of pixel points in the horizontal direction, dividing the actual horizontal length corresponding to the address longitudinal section to obtain the length of the horizontal direction per pixel, and multiplying the horizontal direction pixel number of each stratum by the length of the horizontal direction per pixel to obtain the corresponding mileage.

[0012] Preferably: In the process of changing the section filling color of the CAD drawing in S1, the corresponding drawing legend of each stratum is changed synchronously.

[0013] Preferably: The length in the horizontal direction and the height in the vertical direction of the recorded geological longitudinal section in S2 are expressed as the corresponding actual length or height.

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

[0015] Preferably: in S4, when the k-means algorithm is used for color clustering of the image, the RGB values of k colors in the image are randomly selected as the centroids; the distances between the RGB values of each pixel point in the image and the k centroids are calculated; each pixel point is classified into the nearest centroid; the centroids of the obtained classes are recalculated; and the iteration is performed until the new centroid is equal to or less than the specified threshold value.

[0016] Preferably: in S4, when the upper limit and the lower limit of the tunnel height at different mileage positions are determined, the pixel point position upper and lower limits in the vertical direction are calculated based on the obtained pixel point position set on the tunnel axis; 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 color matrix of the pixel points between the upper and lower limits is read to determine the stratum type of the excavation surface.

[0017] Preferably: in S5, when the stratum proportion of the tunnel excavation surface range is calculated, the proportion is calculated according to the area occupied by each stratum in the excavation surface range and the number of stratum layers.

[0018] Preferably: in S6, when the stratum type identification and thickness calculation of the tunnel along the mileage direction are performed, the stratum type identification and thickness calculation are performed between the highest position and the lowest position in the geological profile; and the stratum thickness and the corresponding mileage are calculated according to the unit pixel length.

[0019] Compared with the prior art, the present application has the beneficial effects that: by converting the CAD drawing into a picture format and then using a clustering algorithm to obtain a geological profile filled with pure colors, the corresponding stratum and stratum parameters can be obtained from the color matrix in the image, and the mapping of image color to geological information is realized. By relying on subsequent computer image processing, the geological information of the geological profile can be extracted, and the present application has the characteristics of strong operability, fast extraction efficiency and high precision, and can provide reliable geological data support for intelligent tunneling and intelligent tunnel construction. BRIEF DESCRIPTION OF DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed in the following embodiment or prior art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0021] Figure 1 is a flow chart of embodiment 1 of the present application.

[0022] Figure 2 is an image img1.

[0023] Figure 3 is an image img2.

[0024] Figure 4 is an image img3.

[0025] Figure 5 is a tunnel axis pixel position extraction result image. DETAILED DESCRIPTION

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

[0027] Embodiment 1

[0028] As shown in Figure 1 , a geological information efficient extraction and calculation method based on a tunnel engineering geological longitudinal section image, comprising the following steps:

[0029] S1: tunnel geological longitudinal section CAD image filling; the stratum filled with non-single color (including gradient color, pattern, etc.) in the tunnel geological longitudinal section CAD image is filled according to pure color, and each pure color corresponds to a single stratum, so as to facilitate subsequent identification of the stratum according to the color difference; at the same time, during the process of changing the section filling color of the CAD image, the corresponding pattern filling legend of each stratum is changed synchronously, which is convenient for subsequent comparison;

[0030] S2: converting the geological longitudinal section CAD image into an image format; selecting the range of the window in the CAD image, and using the printing function to convert the selected tunnel geological longitudinal section interval into an image format, which is denoted as image img1 (see Figure 2 ), and record the length L x of the geological longitudinal section image in the horizontal direction as 3047.50 m and the height L y of the vertical direction as 54.3140 m; 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 an image processing software such as photoshop, the 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, which is white RGB (255, 255, 255) in this embodiment) to form an image img2 (see Figure 3The color of the image generated by the printing function has a certain color difference. The red RGB in the figure is not entirely (255, 0, 0), and the color filled by Photoshop is a single color C1. Whether it is a tunnel axis can be judged by programming using the color of different pixel positions. The judgment logic here is that if the color matrix of the pixel point is not RGB (255, 255, 255), it can be judged that the point is on the tunnel axis, and then the position of the tunnel axis is extracted;

[0032] S4: Tunnel axis removal and tunnel excavation surface stratum extraction; The image img1 is processed, and the color matrix of the pixel point corresponding to the axis position needs to be adjusted to the color matrix of the pixel point in the adjacent area on the axis, to realize the removal of the tunnel axis to form an image img3; The k-means algorithm is used for color clustering of img3 to convert the color with a small color difference in img3 into a single color, and finally achieve the purpose of one color corresponding to each stratum. The processed image is as shown in Figure 4 The tunnel axis pixel position and the size of the tunnel excavation (as shown in Figure 5 The upper limit and the lower limit of the tunnel height at different mileage positions are determined; the color matrix of the pixel points between the upper limit and the lower limit positions is read to determine the stratum type of the excavation surface, and the stratum extraction of the tunnel excavation surface is realized;

[0033] S5: Tunnel excavation surface range stratum proportion calculation; along the horizontal direction, starting from each pixel point position at the upper limit of the tunnel range height, scanning along the vertical direction, the number of pixel points occupied by each stratum in the vertical direction (the thickness of each stratum in the tunnel excavation surface range) is calculated one by one, and finally the proportion of each stratum in the excavation surface range is calculated according to the thickness of each stratum in the excavation surface range;

[0034] S6: Tunnel along mileage direction stratum type identification and thickness calculation; for each pixel point position in the horizontal direction, starting from the upper limit of the height, scanning along the vertical direction, first judging the stratum type by the color matrix of the pixel point, and then calculating the number of pixel points occupied by each stratum in the vertical direction, L px is the length of the vertical direction of a unit pixel, L v is the total number of pixel points in the vertical direction, wherein L px = L y / L v , the number of pixel points in the vertical direction of each stratum multiplied by L px can calculate the thickness of the stratum; L py is the length of the horizontal direction of a unit pixel, L h is the total number of pixel points in the horizontal direction, wherein L py = L h / L h; the mileage conversion is the number of horizontal pixel points multiplied by L py The corresponding mileage can be calculated.

[0035] In this embodiment, the image img2 generated in S3 is read by a program such as matlab software, and the image width (in pixels) and the image height (in pixels) are obtained. The image width corresponds to the horizontal direction of the geological profile, and the image height corresponds to the vertical direction of the geological profile. The starting position is the upper left corner of the image. The tunnel axis position extraction includes the following steps: ① calculating the number of width direction pixel points M and the number of height direction pixel points N; ② i takes a series of integers from 1 to M, and j takes a value 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 horizontal i pixel point is at the pixel point j, and the horizontal i pixel point tunnel axis position extraction is completed; ③ if the color represented by the color matrix at the pixel point (i, j) is C1, j = j + 1, and step ② is repeated; until the vertical positions corresponding to the tunnel axes of the horizontal pixel points 1 to M are all calculated, and the tunnel axis position extraction is completed using L px , L py , and the pixel point positions on the tunnel axis.

[0036] In this embodiment, the k-means algorithm is used to cluster the colors in img3 in S4, including the following operation steps: ① randomly selecting k colors in img3 as the centroids, and k is the number of stratum types; ② calculating the distance between the RGB value of each pixel point in the image and the k centroids, and assigning it to the nearest centroid class; ③ recalculating the centroids of each class obtained; ④ iterating steps ②-③ until the new centroid is equal to or less than the specified threshold value, and the solution is completed; a mapping relationship is established between the k clusters obtained finally and the strata, and a uniform RGB value is assigned to each class 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 operation steps: ① based on the obtained pixel point position set on the tunnel axis, calculating the upper and lower limits of the vertical pixel position, R is the tunnel excavation B radius, R / L py is calculated and is rounded to an integer as Round(R / L py ); ② assuming that the vertical pixel position of a pixel point on the tunnel axis is S py , the upper limit of the tunnel excavation surface range corresponding to this position is S py + Round(R / L py ), and the lower limit of the tunnel excavation surface range is S py - Round(R / L py ); ③ Bi takes a series of integers from 1 to M (M is the number of width direction pixel points M), and j takes a value from S py - Round(R / Lpy ) starts to read the value, 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) is consistent with the color matrix, the number of pixels of the stratum 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 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 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 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 with reference 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 stratum layers; in formula (2), h di 、h ui are the vertical coordinates of the ending pixel point and the starting pixel point of stratum i; D is the tunnel excavation diameter.

[0040] Identify the type of strata and calculate the thickness along the mileage direction of the tunnel in S6. Identify the type of strata and calculate the thickness between the highest and lowest positions in the geological longitudinal section. The following operation steps are included: ①B i Take integers from 1 to M (M is the number of pixels in the width direction), j starts from 1, and reads (B i, 1) is read, according to the determined stratum type, the stratum height is recorded as 1 pixel point, and the pixel point coordinate in the vertical direction is recorded as C jj ; ④ the color matrix of (B i , C jj ) is read, if the color matrix is consistent with the color matrix of (B i , C jj -1), the number of stratum height pixel points is increased by 1 on the basis of the original number, C jj =C jj +1; if the color matrix is not consistent with the color matrix of (B i , C jj -1), the color matrix of (B i , C jj ) is read, according to the determined stratum type, the stratum height is recorded as 1 pixel point, C jj =C jj +1; ⑤ step ④ is repeated, and C jj >N (the number of pixel points in the height direction N) to exit the loop; the stratum type and thickness along the mileage direction of the tunnel can be obtained, the number of pixel points occupied by each stratum in the vertical direction and the starting pixel point coordinate value and the ending pixel point coordinate value of each stratum in the vertical direction can be obtained; the stratum thickness can be obtained by multiplying the number of pixel points occupied by each stratum in the vertical direction by L py

[0041] The basic principle, main features and advantages of the present application are shown and described above, and those skilled in the art should understand that the present application is not limited by the above examples, and the above examples and descriptions in the specification are only to illustrate the principle of the present application, and various changes and improvements can be made to the present application without departing from the spirit and scope of the present application, and these changes and improvements all fall within the scope of the present application.​

Claims

1. A method for efficient extraction and calculation of geological information based on a tunnel engineering geological longitudinal profile, characterized in that, The method comprises the following steps: S1: Tunnel geological longitudinal section CAD diagram filling, filling the stratum in the tunnel geological longitudinal section CAD diagram which is not filled with single color according to pure color, and requiring that each pure color corresponds to a single stratum; S2: Converting the geological longitudinal section CAD diagram into an image format, selecting a window range in the CAD diagram, using a printing function to convert the tunnel geological longitudinal section interval into an image format, denoted as img1, and recording the length in the horizontal direction and the height in the vertical direction of the geological longitudinal section diagram; S3: Image filling and tunnel axis position extraction, using an image processing software to keep the color of the tunnel axis position in the image img1 unchanged, filling the area outside the axis position with other single colors, forming an image img2, and judging whether it is the tunnel axis by using the color of different pixel points, and then extracting the position of the tunnel axis; S4: Tunnel axis removal and tunnel excavation surface stratum extraction, processing the image img1, adjusting the color matrix corresponding to the pixel points of the axis position to the color matrix of the pixel points in the adjacent area of the axis, removing the tunnel axis to form img3, using a k-means algorithm to perform color clustering on the image img3, converting the colors with slight color difference into single colors, finally achieving the purpose that each stratum corresponds to one color, determining the upper limit and lower limit of the tunnel height at different mileage positions of the tunnel according to the pixel point position of the tunnel axis and the size of the tunnel excavation, reading the color matrix of the pixel points between the upper limit and lower limit positions to determine the stratum type of the excavation surface, and realizing the extraction of the stratum of the tunnel excavation surface; S5: Tunnel excavation surface range stratum proportion calculation, starting from each pixel point position at the upper limit of the tunnel range height along the horizontal direction, scanning along the vertical direction, and calculating the number of pixel points occupied by each stratum in the vertical direction one by one, and finally calculating the proportion of each stratum in the excavation surface range according to the thickness of each stratum; S6: Stratum type identification and thickness calculation along the mileage direction of the tunnel, calculating a plurality of vertical positions corresponding to each pixel point in the horizontal direction, starting from the upper limit of the height, scanning along the vertical direction, judging the stratum type by the color matrix at the pixel point, calculating the number of pixel points occupied by each stratum in the vertical direction one by one, and obtaining the thickness of each stratum by multiplying the number of pixel points of each stratum in the vertical direction by the length of the unit pixel in the vertical direction obtained by dividing the total number of pixel points in the vertical direction by the actual vertical height corresponding to the longitudinal section diagram; similarly, the length of the unit pixel in the horizontal direction is obtained by dividing the total number of pixel points in the horizontal direction by the actual horizontal length corresponding to the longitudinal section diagram, and the corresponding mileage is obtained by multiplying the number of pixel points of each stratum in the horizontal direction by the length of the unit pixel in the horizontal direction.

2. The method according to claim 1, wherein the method is characterized by: In the process of changing the section filling color of the CAD diagram in S1, the corresponding drawing filling legend of each stratum is changed synchronously.

3. The method according to claim 1, wherein the method is characterized by: The length in the horizontal direction and the height in the vertical direction of the recorded geological longitudinal section diagram in S2 represent the corresponding actual length or height.

4. The method according to claim 1, wherein the method is characterized by: In S3, the tunnel axis position is extracted by using image processing software to read the image and obtain the image width and height, wherein the image width corresponds to the horizontal direction of the geological profile, and the image height corresponds to the vertical direction of the geological profile. The starting position is the upper left corner of the image. Whether the position is the tunnel axis position is determined by judging whether the color matrix of each pixel point is a single color filled, and the pixel point position set on the tunnel axis is obtained.

5. The method according to claim 1, wherein: In S4, the k-means algorithm is used for color clustering of the image, which includes randomly selecting k colors in the image as the RGB value of the centroid, calculating the distance between the RGB value of each pixel point in the image and the k centroids, and classifying it into the nearest centroid. The centroid of each class obtained is recalculated, and the iteration is performed until the new centroid is equal to or less than the specified threshold value.

6. The method according to claim 4, wherein the method is characterized by: In S4, the upper and lower limits of the tunnel height at different mileage positions are determined 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, 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 stratum type of the excavation surface is determined by reading the color matrix of the pixel points between the upper and lower limits.

7. The method according to claim 1, wherein the method is characterized by: In S5, the stratum proportion calculation of the tunnel excavation surface range is calculated according to the area occupied by each stratum in the excavation surface range and the number of stratum divisions.

8. The method according to claim 1, wherein the method is characterized by: In S6, the stratum type identification and thickness calculation of the tunnel along the mileage direction are performed on the highest position and the lowest position in the geological profile, and the stratum thickness and the corresponding mileage are calculated according to the unit pixel length.

Images