Geological prediction method for tube push bench based on thermal imaging technology

Abstract

The invention discloses a pipe jacking machine geological prediction method based on a thermal imaging technology, and belongs to the technical field of geological recognition, and the method specifically comprises the steps: obtaining an infrared camera image of a pipe jacking machine in a propelling process in real time, carrying out the preprocessing of the infrared camera image, obtaining a propelling region camera image and a to-be-propelled region camera image, and converting the images into corresponding temperature data; calculating a surface temperature difference value of any propelling area after propelling and before propelling, marking the surface temperature difference value as a characteristic value, taking the temperature before propelling as a horizontal axis, taking the temperature after propelling as a longitudinal axis and taking the characteristic value as a vertical axis, constructing a three-dimensional coordinate, generating characteristic points corresponding to all propelling areas, and clustering the characteristic points to generate a plurality of category clusters; performing geologic feature analysis on the propulsion region corresponding to each category cluster to obtain a geologic feature model corresponding to each category cluster; according to the invention, real-time monitoring and prediction of the stratum in front of the pipe jacking machine are realized, so that the safety and efficiency of pipe jacking construction are improved, and the geological risk and the engineering cost are reduced.

Description

Technical Field

[0001] The invention relates to the technical field of geological identification, and in particular to a geological prediction method for a pipe jacking machine based on thermal imaging technology. Background Art

[0002] The pipe jacking machine is a machine that uses hand excavation, mechanical or hydraulic fracturing methods to complete tunnel excavation under the protection of a shield. The pipe jacking machine is placed at the front end of the pipe section to be pushed. Its main functions are to excavate the soil on the front side while maintaining the stability of the water and soil pressure on the front side; secondly, it controls the posture of the pipe jacking machine through the deviation correction device to ensure that the pipe section is pushed in the designed axial direction.

[0003] However, during the advancement of the pipe jacking machine, there will not only be soils of different properties underground, but also gangue or rock faults formed by geological activities. At this time, if the pipe jacking machine is advanced at the set speed, it will aggravate the wear of the drill bit, and even cause the drill bit to break and the cutting part to be damaged, seriously affecting the construction safety of the pipe jacking machine. Using infrared thermal imaging technology to realize the cutting mode recognition of the pipe jacking machine can enable the pipe jacking machine to identify the properties of the soil being pushed during the advancement process, so as to automatically adjust its working state to adapt to the changes in the advancement mode, avoid the occurrence of the above-mentioned dangerous situations, and provide technical guarantees for the reliable operation of the pipe jacking machine. Summary of the invention

[0004] The purpose of the present invention is to provide a geological prediction method for a pipe jacking machine based on thermal imaging technology to solve the following technical problems:

[0005] During the advancement of the pipe jacking machine, there will be not only soil of different properties underground, but also gangue or rock faults formed by geological activities. If the pipe jacking machine is advanced at the set speed, it will aggravate the wear of the drill bit, and even cause the drill bit to break and the cutting part to be damaged, which will seriously affect the construction safety of the pipe jacking machine.

[0006] The purpose of the present invention can be achieved through the following technical solutions:

[0007] The geological prediction method of pipe jacking machine based on thermal imaging technology includes the following steps:

[0008] S1, acquiring infrared camera images of the pipe jacking machine in the advancement process in real time, preprocessing the infrared camera images to obtain infrared camera images of the advancement area and infrared camera images of the area to be advanced, and converting the infrared camera images of the advancement area and the infrared camera images of the area to be advanced into corresponding surface temperature data;

[0009] S2, select any advancing area, calculate the surface temperature difference between the advancing area and the unadvanced area and mark it as the characteristic value, obtain the characteristic values ​​of all advancing areas, respectively, with the surface temperature before advancement as the horizontal axis, the surface temperature after advancement as the vertical axis, and the characteristic value as the vertical axis, construct three-dimensional coordinates, generate characteristic points corresponding to all advancing areas, select any characteristic point as the center, set the clustering radius R, calculate the characteristic point density L within the clustering radius R, obtain the mean characteristic point density within the clustering radius R of all characteristic points, mark the mean characteristic point density as MinL, if there is any characteristic point with a characteristic point density L greater than MinL within the radius R of the characteristic point, mark the characteristic point as a core point, and generate a category cluster with the core point as the center;

[0010] S3, analyzing the geological characteristics of the advancement area corresponding to each category cluster to obtain a geological characteristic model corresponding to each category cluster.

[0011] As a further solution of the present invention: in S1, the rotation speed and propulsion speed of the pipe jacking machine cutter disc during the propulsion process remain unchanged.

[0012] As a further solution of the present invention: in S1, the specific process of pretreatment is:

[0013] The infrared camera image is gray-processed to obtain a gray-scale image, the gray-scale image is denoised, edge detection is performed on the gray-scale image after denoising, and the gray-scale image after edge detection is binarized, the area to be advanced is divided into black, and the advancement area is divided into white, to generate a binary image.

[0014] As a further solution of the present invention: In S2, the specific process of setting the clustering radius R is:

[0015] Select any feature point and take it as the center, calculate the Euclidean distance I between the feature point and any other feature point, sum each Euclidean distance to get M, and get the cluster radius R based on the value M. The calculation formula is as follows:

[0016]

[0017]

[0018] Among them, M is the sum of the Euclidean distance data values ​​of all feature points, and I is the Euclidean distance between any feature points.

[0019] As a further solution of the present invention: in S2, the calculation formula for calculating the density of feature points within the clustering radius R is:

[0020] L=3N / (4πR 3 );

[0021] Where N is the number of feature points within the cluster radius R.

[0022] As a further solution of the present invention: in S2, if there is a non-core point in any category cluster whose density L within the clustering radius R is also greater than MinL, the category cluster generated by the non-core point is merged with the original category cluster to generate several category clusters.

[0023] As a further solution of the present invention: S3 also includes manually determining the geological characteristic model corresponding to each category cluster, and dividing the geological characteristic model into a normal geological characteristic model and an abnormal geological model.

[0024] As a further solution of the present invention: it also includes real-time acquisition of temperature data during the advancement process and bringing it into the geological feature model for identification. If the identification result is an abnormal geological model, an early warning is issued.

[0025] Beneficial effects of the present invention:

[0026] First, by installing a thermal imager inside the cutterhead of the pipe jacking machine, the heat distribution generated by the cutterhead cutting different soil layers is monitored in real time. Secondly, during the advancement of the pipe jacking machine, the thermal imager is used to obtain infrared thermal images in front of the formation and convert these images into digital data. Then, the acquired digital data is analyzed using computer processing technology, the temperature characteristics of the formation are extracted, clustered according to the temperature distribution law of the formation, and the clustered bottom layer is geologically analyzed to build a geological model. The real-time temperature data is compared and analyzed with the constructed model to infer and predict the physical properties of the formation, such as the type of rock formation. Finally, when possible geological obstacles or abnormal conditions are detected, the system can issue an alarm and record relevant data to guide subsequent pipe jacking machine operations. According to the real-time analysis results provided by the system, operators can adjust the propulsion speed and direction of the pipe jacking machine and the rotation speed of the cutter head of the pipe jacking machine to reduce or avoid the impact of geological obstacles. Thermal imaging technology is used to achieve real-time monitoring and prediction of the strata in front of the pipe jacking machine, and the jacking parameters of the pipe jacking machine are adjusted in real time according to the monitoring results. This not only improves the safety and efficiency of pipe jacking construction, but also effectively reduces geological risks and engineering costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] The present invention will be further described below in conjunction with the accompanying drawings.

[0028] Figure 1 The present invention is a schematic flow chart of a method for geological prediction of a pipe jacking machine based on thermal imaging technology. DETAILED DESCRIPTION

[0029] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0030] See also Figure 1 As shown, the present invention is a geological prediction method for a pipe jacking machine based on thermal imaging technology. A thermal imager is installed inside the cutter head of the pipe jacking machine, and the method includes the following steps:

[0031] S1, real-time acquisition of infrared camera images of the pipe jacking machine during the advancement process, pre-processing the infrared camera images to obtain infrared camera images of the advanced area and the infrared camera images of the area to be advanced, and converting the infrared camera images of the advanced area and the infrared camera images of the area to be advanced into corresponding surface temperature data;

[0032] S2, select any advancing area, calculate the surface temperature difference between the advancing area and the unadvanced area and mark it as the characteristic value, obtain the characteristic values ​​of all advancing areas, respectively, with the surface temperature before advancement as the horizontal axis, the surface temperature after advancement as the vertical axis, and the characteristic value as the vertical axis, construct three-dimensional coordinates, generate characteristic points corresponding to all advancing areas, select any characteristic point as the center, set the clustering radius R, calculate the characteristic point density L within the clustering radius R, obtain the mean characteristic point density within the clustering radius R of all characteristic points, mark the mean characteristic point density as MinL, if there is any characteristic point with a characteristic point density L greater than MinL within the radius R of the characteristic point, mark the characteristic point as a core point, and generate a category cluster with the core point as the center;

[0033] S3, analyzing the geological characteristics of the advancement area corresponding to each category cluster to obtain a geological characteristic model corresponding to each category cluster.

[0034] First, by installing a thermal imager inside the cutterhead of the pipe jacking machine, the heat distribution generated by the cutterhead cutting different soil layers is monitored in real time. Secondly, during the advancement of the pipe jacking machine, the thermal imager is used to obtain infrared thermal images in front of the formation and convert these images into digital data. Then, the acquired digital data is analyzed using computer processing technology to extract the temperature characteristics and distribution patterns of the formation. The formation is clustered according to the temperature distribution pattern and the clustered bottom layer is geologically analyzed to build a geological model. The real-time temperature data is compared and analyzed with the constructed model to infer and predict the physical properties of the formation, such as the type of rock formation. Finally, when possible geological obstacles or abnormal conditions are detected, the system can issue an alarm and record relevant data to guide subsequent pipe jacking machine operations. According to the real-time analysis results provided by the system, operators can adjust the propulsion speed and direction of the pipe jacking machine and the rotation speed of the cutter head of the pipe jacking machine to reduce or avoid the impact of geological obstacles. Thermal imaging technology is used to achieve real-time monitoring and prediction of the strata in front of the pipe jacking machine, and the jacking parameters of the pipe jacking machine are adjusted in real time according to the monitoring results. This not only improves the safety and efficiency of pipe jacking construction, but also effectively reduces geological risks and engineering costs.

[0035] In a preferred embodiment of the present invention, in S1, the drill bit rotation speed and the propulsion speed of the pipe jacking machine remain unchanged during the propulsion process.

[0036] It is understandable that during the advancement of the pipe jacking machine, the geological parameters of the advancement area are constantly changing. Therefore, while keeping the drill bit speed and advancement speed of the pipe jacking machine unchanged, the characteristic values ​​of the advancement area are only related to the geological parameters of the advancement area. It is understandable that the characteristic values ​​obtained after advancement of loose sand and dense clay layers are different.

[0037] In a preferred embodiment of the present invention, in S1, the specific process of preprocessing is:

[0038] The infrared camera image is gray-processed to obtain a gray-scale image, the gray-scale image is denoised, edge detection is performed on the gray-scale image after denoising, and the gray-scale image after edge detection is binarized, the area to be advanced is divided into black, and the advancement area is divided into white, to generate a binary image.

[0039] Converting infrared camera images to grayscale images simplifies image data, reduces computational complexity, and makes subsequent processing (such as noise reduction and edge detection) more efficient. Denoising grayscale images can remove noise or interference in the image, improve image quality, and avoid image noise interfering with the effect of edge detection, resulting in inaccurate final results. Edge detection is performed on the denoised grayscale image to extract significant boundaries in the image. Edge detection helps identify the contours and shapes of objects in the image and is an important step in image analysis. Common edge detection algorithms include the Canny algorithm and the Sobel operator. The grayscale image after edge detection is binarized to generate a binary image. This step divides the image into black and white areas, thereby simplifying the image representation and facilitating further analysis. By dividing the area to be advanced into black and the area to be advanced into white, different areas can be clearly represented and distinguished.

[0040] In a preferred embodiment of the present invention, in S2, the specific process of setting the cluster radius R is:

[0041] Select any feature point and take it as the center, calculate the Euclidean distance I between the feature point and any other feature point, sum each Euclidean distance to get M, and get the cluster radius R based on the value M. The calculation formula is as follows:

[0042]

[0043]

[0044] Among them, M is the sum of the Euclidean distance data values ​​of all feature points, and I is the Euclidean distance between any feature points.

[0045] In a preferred embodiment of the present invention, in S2, the calculation formula for calculating the density of feature points within the clustering radius R is:

[0046] L=3N / (4πR 3 );

[0047] Where N is the number of feature points within the cluster radius R.

[0048] In a preferred embodiment of the present invention, in S2, if there is a non-core point in any category cluster whose density L within the clustering radius R is also greater than MinL, the category cluster generated by the non-core point is merged with the original category cluster to generate several category clusters.

[0049] In a preferred embodiment of the present invention, S3 further includes manually determining the geological feature model corresponding to each category cluster, and dividing the geological feature model into a normal geological feature model and an abnormal geological model.

[0050] It is understandable that during the advancement of the pipe jacking machine, there will not only be soil of different properties underground, but also gangue or rock faults formed by geological activities. At this time, if the pipe jacking machine is advanced at the set speed, it will aggravate the wear of the drill bit, and even cause the drill bit to break and the cutting part to be damaged, seriously affecting the safety of the pipe jacking machine construction. Therefore, a geological characteristic model can be constructed according to the temperature data changes during the advancement of the actual pipe jacking machine, and then manually determined to determine the abnormal geological model, so as to effectively predict and prevent geological obstacles, reduce equipment damage, reduce the cost of maintenance and replacement of parts, improve the safety and efficiency of pipe jacking construction, and effectively reduce geological risks and engineering costs.

[0051] In a preferred embodiment of the present invention, it also includes real-time acquisition of temperature data during the advancement process and bringing it into the geological feature model for identification. If the identification result is an abnormal geological model, an early warning is issued.

[0052] It can be understood that the temperature data acquired in real time is compared and analyzed with the model based on the geological characteristic model to infer and predict the physical properties of the stratum, such as rock type, sand type, etc. When possible geological obstacles or abnormal conditions are detected, the propulsion speed and direction of the pipe jacking machine and the rotation speed of the cutter head of the pipe jacking machine can be adjusted according to the real-time analysis results provided by the system to reduce or avoid the impact of geological obstacles.

[0053] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A geological prediction method for pipe jacking machine based on thermal imaging technology, characterized in that: Installing a thermal imager inside the cutter head of a pipe jacking machine includes the following steps: S1, acquiring infrared camera images of the pipe jacking machine in the advancement process in real time, preprocessing the infrared camera images to obtain infrared camera images of the advancement area and infrared camera images of the area to be advanced, and converting the infrared camera images of the advancement area and the infrared camera images of the area to be advanced into corresponding surface temperature data; S2, select any advancing area, calculate the surface temperature difference between the advancing area and the unadvanced area and mark it as the characteristic value, obtain the characteristic values ​​of all advancing areas, respectively, with the surface temperature before advancement as the horizontal axis, the surface temperature after advancement as the vertical axis, and the characteristic value as the vertical axis, construct three-dimensional coordinates, generate characteristic points corresponding to all advancing areas, select any characteristic point as the center, set the clustering radius R, calculate the characteristic point density L within the clustering radius R, obtain the mean characteristic point density within the clustering radius R of all characteristic points, mark the mean characteristic point density as MinL, if there is any characteristic point with a characteristic point density L greater than MinL within the radius R of the characteristic point, mark the characteristic point as a core point, and generate a category cluster with the core point as the center; S3, analyzing the geological characteristics of the advancement area corresponding to each category cluster to obtain a geological characteristic model corresponding to each category cluster.

2. The method for geological prediction of pipe jacking machine based on thermal imaging technology according to claim 1 is characterized in that: In S1, the rotation speed and propulsion speed of the pipe jacking machine cutter disc remain unchanged during the propulsion process.

3. The geological prediction method for pipe jacking machine based on thermal imaging technology according to claim 1 is characterized in that: In S1, the specific process of preprocessing is: The infrared camera image is gray-processed to obtain a gray-scale image, the gray-scale image is denoised, edge detection is performed on the gray-scale image after denoising, and the gray-scale image after edge detection is binarized, the area to be advanced is divided into black, and the advancement area is divided into white, to generate a binary image.

4. The method for geological prediction of pipe jacking machine based on thermal imaging technology according to claim 1 is characterized in that: In S2, the specific process of setting the cluster radius R is: Select any feature point and take it as the center, calculate the Euclidean distance I between the feature point and any other feature point, sum each Euclidean distance to get M, and get the cluster radius R based on the value M. The calculation formula is as follows: Among them, M is the sum of the Euclidean distance data values ​​of all feature points, and I is the Euclidean distance between any feature points.

5. The method for geological prediction of pipe jacking machine based on thermal imaging technology according to claim 1 is characterized in that: In S2, the calculation formula for calculating the density of feature points within the cluster radius R is: L=3N / (4πR 3 ); Where N is the number of feature points within the cluster radius R.

6. The geological prediction method for pipe jacking machine based on thermal imaging technology according to claim 1 is characterized in that: In S2, if there is a non-core point in any category cluster whose density L within the clustering radius R is also greater than MinL, the category cluster generated by the non-core point is merged with the original category cluster to generate several category clusters.

7. The method for geological prediction of pipe jacking machine based on thermal imaging technology according to claim 1 is characterized in that: The S3 also includes manually determining the geological feature model corresponding to each category cluster, and dividing the geological feature model into a normal geological feature model and an abnormal geological model.

8. The method for geological prediction of pipe jacking machine based on thermal imaging technology according to claim 1 is characterized in that: It also includes real-time acquisition of temperature data during the advancement process and bringing it into the geological feature model for identification. If the identification result is an abnormal geological model, an early warning is issued.

Images