Underground railway station deep foundation pit construction safety supervision method and system

Abstract

The invention discloses an underground railway station deep foundation pit construction safety supervision method and system, and the method comprises the steps: carrying out the real-time shooting of concrete in an underground railway station deep foundation pit through high-definition shooting equipment, and obtaining the image of the concrete in the foundation pit. According to the method, crack area detection is carried out through the deep learning technology, the length information, width information and depth information of the cracks are extracted, the crack information set is formed, and due to years of crack research and development, experts find multiple types of cracks, and the crack detection efficiency is improved. The types of the cracks are greatly related to the length characteristics, the width characteristics and the depth characteristics of the cracks, so that the members of the expert database propose a foundation pit safety monitoring model, input the real-time crack information set into the foundation pit safety monitoring model, output the types of the cracks and obtain the risk value of the foundation pit; the risk value of the foundation pit seriously relates to the reliability of the construction safety of the foundation pit, and the accuracy of the construction safety supervision of the deep foundation pit of the underground railway station is improved.

Description

Technical Field

[0001] The invention relates to the technical field of safety supervision of foundation pit construction, and in particular to a method and system for safety supervision of deep foundation pit construction of an underground railway station. Background Art

[0002] With the acceleration of urbanization and the continuous deepening of underground space resource development, the construction of underground railway stations has become an important part of urban transportation development. In the foundation pit construction of underground railway stations, the support structure of the foundation pit is the key part to ensure the stability of the foundation pit. According to the design requirements, concrete is needed to enhance the support strength of the foundation pit to avoid soil collapse around the foundation pit. Therefore, the monitoring of foundation pit concrete cracks plays a significant role in the safety supervision of foundation pit construction.

[0003] Chinese patent CN110197483A discloses a deep foundation pit crack detection method based on video signals, including obtaining deep foundation pit crack sample images, processing samples and obtaining crack training sets and verification sets, training deep foundation pit crack detection models based on the training sets, optimizing model parameters using crack verification sets, and automatically detecting the collected images based on the deep foundation pit crack detection model. The present invention can automatically detect cracks in deep foundation pits in video signals, has good real-time performance and high accuracy, can effectively detect cracks in deep foundation pits, and can adapt to changes in deep foundation pit background and environment.

[0004] However, when processing deep foundation pit crack sample images, the above patent lacks denoising and enhancement processing for the images, and is unable to segment the crack area, resulting in the inability to accurately locate and identify the crack area, and the detection accuracy is low. In addition, the above patent also lacks analysis of the expansion rate of the cracks, and is unable to determine whether the cracks are normal cracks or abnormal cracks. It has low applicability and is difficult to meet the needs of staff. Summary of the invention

[0005] In order to solve the above technical problems, a method and system for safety supervision of deep foundation pit construction of underground railway stations are provided. This technical solution solves the problem that the above patent proposed in the above background technology lacks denoising and enhancement processing of the image when processing deep foundation pit crack sample images, and cannot segment the crack area, resulting in the inability to accurately locate and identify the crack area, and the detection accuracy is low. In addition, the above patent also lacks analysis of the expansion rate of the cracks, and cannot determine whether the cracks are normal cracks or abnormal cracks, and has low applicability.

[0006] In order to achieve the above purpose, the technical solution adopted by the present invention is: A method for safety supervision of deep foundation pit construction of underground railway stations, comprising: Using high-definition shooting equipment to shoot the concrete in the deep foundation pit of the underground railway station in real time to obtain the concrete image in the foundation pit; receiving the foundation pit concrete image and preprocessing the image, the preprocessing includes image denoising, image enhancement and image segmentation to obtain the preprocessed image; Analyze the crack area in the preprocessed foundation pit concrete image, and extract the length, width and depth information of the crack to form a crack information set; Retrieve a pre-set foundation pit safety monitoring model from the database, input the crack information set into the foundation pit safety monitoring model, output the crack type, and obtain the risk value of the foundation pit; The reliability of foundation pit construction safety is analyzed based on the foundation pit risk value.

[0007] Preferably, the image denoising specifically comprises the following steps: Adaptive wavelet threshold denoising is performed on foundation pit concrete images; By constructing a probability model of wavelet coefficients, the optimal wavelet threshold is determined using Bayesian estimation. The wavelet coefficients are processed with adaptive threshold and then reconstructed by wavelet to obtain a denoised image.

[0008] Preferably, the image enhancement specifically comprises the following steps: Performing adaptive histogram equalization processing on the denoised image; Determine the cumulative distribution function of the local area by calculating the grayscale histogram of the denoised image; Based on the cumulative distribution function, the grayscale mapping relationship of the local area is adaptively adjusted to obtain an enhanced image.

[0009] Preferably, the image segmentation specifically comprises the following steps: Segmenting the enhanced image into multiple superpixels using a superpixel segmentation algorithm; Determine the similarity matrix between superpixels as the edge weight of the undirected graph, and construct a superpixel graph cut undirected graph; In combination with the pre-set probability distribution of the text area, the global optimal solution of the superpixel graph cut undirected graph is solved by the maximum flow minimum cut algorithm; The segmentation result of the crack area is obtained to obtain the preprocessed image.

[0010] Preferably, the analysis of the crack area in the preprocessed foundation pit concrete image specifically includes the following steps: marking the area of ​​the foundation pit concrete image in units of lines; The labeled images are combined into a training set and trained through the object detection model until convergence; The segmented image blocks are put into the trained target detection model to perform target detection in the crack area, and the coordinates of the crack area in each image block are obtained and output; Based on the coordinates of the complete crack area, each complete crack area in the foundation pit concrete image is obtained; Based on the crack area in the foundation pit concrete image, the regional coordinates of the foundation pit concrete image are marked and formed into a training set; the hybrid model composed of CNN and LSTM based on the deep learning attention mechanism is trained until convergence; The crack area of ​​the segmented image block is placed into the trained hybrid model for crack recognition to obtain the length, width and depth information of the crack.

[0011] Preferably, the foundation pit safety monitoring model is: Among them, P j is the matching degree between the input fracture information set data and the jth fracture type, N j is the total number of historical fracture information set data corresponding to the jth fracture type, N0 is the total number of features of the input fracture information set data, N 同 is the total number of identical features between the feature data of the input fracture information set data and the historical fracture set data corresponding to the jth fracture type, α' l is the correlation weight between the feature data of the j-th fracture type and the l-th input fracture set data and the same feature in the historical fracture set data corresponding to the j-th fracture type, max(N j , N0) is the maximum value function.

[0012] Preferably, the analysis of the reliability of foundation pit construction safety based on the foundation pit risk value specifically includes the following steps: Compare the foundation pit risk value with the preset threshold in the system; If the foundation pit risk value is greater than or equal to the preset threshold, the foundation pit has a greater risk and the safety reliability of the foundation pit is low; If the foundation pit risk value is less than the preset threshold, the foundation pit has a smaller risk and a higher safety reliability; Take measures to deal with low and high reliability respectively.

[0013] Preferably, the taking measures for the foundation pit with low reliability specifically includes the following steps: Use a mixing machine to proportion the concrete raw materials; Pour the well-proportioned concrete to the dangerous crack area; Maintain the poured concrete; The foundation pit with higher reliability specifically includes the following steps: The images of the normal crack area were collected continuously for one week; Repeat the above analysis operation on the collected image to obtain the width information, length information and depth information of the crack; Calculate the crack size information within one week based on the width information, length information and depth information; The crack size information before and after is calculated, and the expansion rate of the crack before and after is obtained by dividing the time difference before and after. Sum all the expansion rates and divide by the number to get the average rate of crack expansion; comparing the average rate of crack expansion with a second threshold; If the average rate of crack expansion is greater than or equal to the second threshold, the crack at that location is protected and reinforced; If the average rate of crack expansion is less than the second threshold, it is considered normal expansion and no measures are taken.

[0014] On the other hand, the present application also provides a safety supervision system for deep foundation pit construction of underground railway stations, comprising: A shooting module, wherein the shooting module is used to shoot the concrete in the deep foundation pit of the underground railway station in real time using a high-definition shooting device to obtain an image of the concrete in the foundation pit; An image preprocessing module, wherein the image preprocessing module internally integrates a first image processing unit, a second image processing unit and a third image processing unit; A crack information extraction module, which is used to analyze the crack area in the preprocessed foundation pit concrete image and extract the length information, width information and depth information of the crack to form a crack information set; A foundation pit risk value acquisition module, which is used to retrieve a pre-set foundation pit safety monitoring model from a database, input a set of crack information into the foundation pit safety monitoring model, output crack types, and obtain a risk value of the foundation pit; A foundation pit reliability evaluation module, wherein the foundation pit reliability evaluation module analyzes the reliability of foundation pit construction safety based on the foundation pit risk value; A first image processing unit, wherein the first image processing unit is used for image denoising; A second image processing unit, wherein the second image processing unit is used for image enhancement; A third image processing unit is used for image segmentation.

[0015] Compared with the prior art, the present invention provides a method and system for safety supervision of deep foundation pit construction of underground railway stations, which has the following beneficial effects: The present invention adopts image processing technology, collects foundation pit concrete images, removes noise in the foundation pit concrete images to improve the accuracy of subsequent crack identification, and performs image enhancement processing on the denoised image to enhance the image contrast, improve image clarity, and improve the effect of crack identification. The image is divided into different regions to better identify and locate the crack region, and then the crack region is detected through deep learning technology, and the length information, width information and depth information of the crack are extracted to form a crack information set. After years of crack research and development, experts have discovered a variety of crack types, and these crack types are greatly related to the length characteristics, width characteristics and depth characteristics of the cracks. Therefore, members of the expert database propose a foundation pit safety monitoring model, input the real-time crack information set into the foundation pit safety monitoring model, output the crack type, and obtain the risk value of the foundation pit. The risk value of the foundation pit is seriously related to the reliability of the safety of the foundation pit construction, improves the accuracy of the safety supervision of the deep foundation pit construction of the underground railway station, and meets the needs of the staff. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a schematic diagram of the deep foundation pit construction safety supervision method of the present invention; Figure 2 Schematic diagram of the method for image denoising in the present invention; Figure 3 is a schematic diagram of the image enhancement method in the present invention; Figure 4 It is a schematic diagram of the method for image segmentation in the present invention; Figure 5 It is a schematic diagram of the method for analyzing the safety reliability of foundation pit construction in the present invention. DETAILED DESCRIPTION

[0017] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art may think of other obvious variations.

[0018] Please refer to Figure 1-Figure 5 As shown, a method for safety supervision of deep foundation pit construction of underground railway stations comprises: Use high-definition camera equipment to take real-time photos of the concrete in the deep foundation pit of the underground railway station to obtain images of the concrete in the foundation pit; receive the concrete images of the foundation pit and pre-process the images, including image denoising, image enhancement and image segmentation, to obtain pre-processed images; Analyze the crack area in the preprocessed foundation pit concrete image, and extract the length, width and depth information of the crack to form a crack information set; Retrieve a pre-set foundation pit safety monitoring model from the database, input the crack information set into the foundation pit safety monitoring model, output the crack type, and obtain the risk value of the foundation pit; The reliability of foundation pit construction safety is analyzed based on the foundation pit risk value.

[0019] It can be understood by those skilled in the art that, in the foundation pit construction of underground railway stations, the support structure of the foundation pit is a key part to ensure the stability of the foundation pit. According to the design requirements, concrete is needed to enhance the support strength of the foundation pit to avoid soil collapse around the foundation pit. Therefore, monitoring of foundation pit concrete cracks plays a significant role in the safety supervision of foundation pit construction. The present invention adopts image processing technology to collect foundation pit concrete images and remove noise from the foundation pit concrete images to improve the accuracy of subsequent crack recognition. In order to enhance the contrast of the image, improve the image clarity, and improve the effect of crack recognition, the denoised image is subjected to image enhancement processing, and the image is divided into different areas for better The crack area is identified and located, and then the crack area is detected through deep learning technology, and the length, width and depth information of the cracks are extracted to form a crack information set. After years of crack research and development, experts have discovered many types of cracks, and these crack types are closely related to the length characteristics, width characteristics and depth characteristics of the cracks. Therefore, members of the expert database proposed a foundation pit safety monitoring model, and input the real-time crack information set into the foundation pit safety monitoring model, output the crack type, and obtain the risk value of the foundation pit. The risk value of the foundation pit is seriously related to the reliability of the safety of the foundation pit construction, which improves the accuracy of safety supervision of deep foundation pit construction of underground railway stations and meets the needs of staff.

[0020] Image denoising specifically includes the following steps: Adaptive wavelet threshold denoising is performed on foundation pit concrete images; By constructing a probability model of wavelet coefficients, the optimal wavelet threshold is determined using Bayesian estimation. The wavelet coefficients are processed with adaptive threshold and then reconstructed by wavelet to obtain a denoised image.

[0021] Image enhancement specifically includes the following steps: Perform adaptive histogram equalization on the denoised image; By calculating the grayscale histogram of the denoised image, the cumulative distribution function of the local area is determined; Based on the cumulative distribution function, the grayscale mapping relationship of the local area is adaptively adjusted to obtain an enhanced image.

[0022] Image segmentation specifically includes the following steps: The enhanced image is segmented into multiple superpixels by a superpixel segmentation algorithm; Determine the similarity matrix between superpixels as the edge weight of the undirected graph, and construct a superpixel graph cut undirected graph; Combined with the pre-set probability distribution of the text area, the global optimal solution of the superpixel graph cut undirected graph is solved by the maximum flow minimum cut algorithm; The segmentation result of the crack area is obtained and the preprocessed image is obtained.

[0023] The analysis of the crack area in the preprocessed foundation pit concrete image specifically includes the following steps: Mark the area of ​​the foundation pit concrete image in lines; The labeled images are combined into a training set and trained through the object detection model until convergence; The segmented image blocks are put into the trained target detection model to perform target detection in the crack area, and the coordinates of the crack area in each image block are obtained and output; Based on the coordinates of the complete crack area, each complete crack area in the foundation pit concrete image is obtained; Based on the crack area in the foundation pit concrete image, the regional coordinates of the foundation pit concrete image are marked and formed into a training set; the hybrid model composed of CNN and LSTM based on the deep learning attention mechanism is trained until convergence; The crack area of ​​the segmented image block is placed into the trained hybrid model for crack recognition to obtain the length, width and depth information of the crack.

[0024] The foundation pit safety monitoring model is: Among them, P j is the matching degree between the input fracture information set data and the jth fracture type, N j is the total number of historical fracture information set data corresponding to the jth fracture type, N0 is the total number of features of the input fracture information set data, N 同 is the total number of identical features between the feature data of the input fracture information set data and the historical fracture set data corresponding to the jth fracture type, α' l is the correlation weight between the feature data of the j-th fracture type and the l-th input fracture set data and the same feature in the historical fracture set data corresponding to the j-th fracture type, max(N j , N0) is the maximum value function.

[0025] The reliability analysis of foundation pit construction safety based on foundation pit risk value specifically includes the following steps: Compare the foundation pit risk value with the preset threshold in the system; If the foundation pit risk value is greater than or equal to the preset threshold, the foundation pit has a greater risk and the safety reliability of the foundation pit is low; If the foundation pit risk value is less than the preset threshold, the foundation pit has a smaller risk and a higher safety reliability; Take measures to deal with low and high reliability respectively.

[0026] The specific measures taken for foundation pits with low reliability include the following steps: Use a mixing machine to proportion the concrete raw materials; Pour the well-proportioned concrete to the dangerous crack area; Maintain the poured concrete; The specific steps for the foundation pit with higher reliability include the following: The images of the normal crack area were collected continuously for one week; Repeat the above analysis operation on the collected image to obtain the width information, length information and depth information of the crack; Calculate the crack size information within one week based on the width information, length information and depth information; The crack size information before and after is calculated, and the expansion rate of the crack before and after is obtained by dividing the time difference before and after. Sum all the expansion rates and divide by the number to get the average rate of crack expansion; comparing the average rate of crack expansion with a second threshold; If the average rate of crack expansion is greater than or equal to the second threshold, the crack at that location is protected and reinforced; If the average rate of crack expansion is less than the second threshold, it is considered normal expansion and no measures are taken.

[0027] On the other hand, the present application also provides a safety supervision system for deep foundation pit construction of underground railway stations, comprising: A shooting module is used to shoot the concrete in the deep foundation pit of the underground railway station in real time using high-definition shooting equipment to obtain images of the concrete in the foundation pit; An image preprocessing module, the internal integration of the image preprocessing module includes a first image processing unit, a second image processing unit and a third image processing unit; A crack information extraction module is used to analyze the crack area in the preprocessed foundation pit concrete image and extract the length information, width information and depth information of the crack to form a crack information set; A foundation pit risk value acquisition module, which is used to retrieve a pre-set foundation pit safety monitoring model from a database, input a set of crack information into the foundation pit safety monitoring model, output the crack type, and obtain the risk value of the foundation pit; a foundation pit reliability evaluation module, which analyzes the reliability of foundation pit construction safety based on the foundation pit risk value; a first image processing unit, which is used for image denoising; A second image processing unit, the second image processing unit is used for image enhancement; The third image processing unit is used for image segmentation.

[0028] In summary, in the foundation pit construction of underground railway stations, the support structure of the foundation pit is the key part to ensure the stability of the foundation pit. According to the design requirements, concrete is needed to enhance the support strength of the foundation pit to avoid soil collapse around the foundation pit. Therefore, monitoring of foundation pit concrete cracks plays a significant role in the safety supervision of foundation pit construction. The present invention adopts image processing technology to collect foundation pit concrete images and remove noise from foundation pit concrete images to improve the accuracy of subsequent crack recognition. In order to enhance the contrast of the image, improve the image clarity, and improve the effect of crack recognition, the denoised image is subjected to image enhancement processing, and the image is divided into different areas for better recognition and positioning. Crack area, and then use deep learning technology to detect crack area, and extract the length information, width information and depth information of the crack, and form a crack information set. After years of crack research and development, experts have discovered many types of cracks, and these crack types are closely related to the length characteristics, width characteristics and depth characteristics of the cracks. Therefore, members of the expert database proposed a foundation pit safety monitoring model, and input the real-time crack information set into the foundation pit safety monitoring model, output the crack type, and obtain the risk value of the foundation pit. The risk value of the foundation pit is seriously related to the reliability of the safety of the foundation pit construction, which improves the accuracy of safety supervision of deep foundation pit construction of underground railway stations and meets the needs of staff.

[0029] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions only describe the principles of the present invention. The present invention may be subject to various changes and improvements without departing from the spirit and scope of the present invention. These changes and improvements fall within the scope of the present invention. The scope of protection claimed by the present invention is defined by the attached claims and their equivalents.

Claims

1. A method for safety supervision of deep foundation pit construction of underground railway stations, characterized in that: include: Use high-definition camera equipment to take real-time photos of the concrete in the deep foundation pit of the underground railway station to obtain images of the concrete in the foundation pit; receiving a foundation pit concrete image and performing preprocessing on the image, wherein the preprocessing includes image denoising, image enhancement and image segmentation, and obtaining a preprocessed image; Analyze the crack area in the preprocessed foundation pit concrete image, and extract the length, width and depth information of the crack to form a crack information set; Retrieve a pre-set foundation pit safety monitoring model from the database, input the crack information set into the foundation pit safety monitoring model, output the crack type, and obtain the risk value of the foundation pit; The reliability of foundation pit construction safety is analyzed based on the foundation pit risk value.

2. A method for safety supervision of deep foundation pit construction of underground railway stations according to claim 1, characterized in that: The image denoising specifically comprises the following steps: Adaptive wavelet threshold denoising is performed on foundation pit concrete images; By constructing a probability model of wavelet coefficients, the optimal wavelet threshold is determined using Bayesian estimation. The wavelet coefficients are processed with adaptive threshold and then reconstructed by wavelet to obtain a denoised image.

3. A method for safety supervision of deep foundation pit construction of underground railway stations according to claim 2, characterized in that: The image enhancement specifically comprises the following steps: Performing adaptive histogram equalization processing on the denoised image; Determine the cumulative distribution function of the local area by calculating the grayscale histogram of the denoised image; Based on the cumulative distribution function, the grayscale mapping relationship of the local area is adaptively adjusted to obtain an enhanced image.

4. A method for safety supervision of deep foundation pit construction of underground railway stations according to claim 3, characterized in that: The image segmentation specifically comprises the following steps: Segmenting the enhanced image into multiple superpixels using a superpixel segmentation algorithm; Determine the similarity matrix between superpixels as the edge weight of the undirected graph, and construct a superpixel graph cut undirected graph; In combination with the pre-set probability distribution of the text area, the global optimal solution of the superpixel graph cut undirected graph is solved by the maximum flow minimum cut algorithm; The segmentation result of the crack area is obtained to obtain the preprocessed image.

5. A method for safety supervision of deep foundation pit construction of underground railway stations according to claim 4, characterized in that: The analysis of the crack area in the preprocessed foundation pit concrete image specifically includes the following steps: Mark the area of ​​the foundation pit concrete image in lines; The labeled images are combined into a training set and trained through the object detection model until convergence; The segmented image blocks are put into the trained target detection model to perform target detection in the crack area, and the coordinates of the crack area in each image block are obtained and output; Based on the coordinates of the complete crack area, each complete crack area in the foundation pit concrete image is obtained; Based on the crack area in the foundation pit concrete image, the regional coordinates of the foundation pit concrete image are marked and formed into a training set; Train a hybrid model consisting of CNN and LSTM based on deep learning attention mechanism until convergence; The crack area of ​​the segmented image block is placed into the trained hybrid model for crack recognition to obtain the length, width and depth information of the crack.

6. A method for safety supervision of deep foundation pit construction of underground railway stations according to claim 5, characterized in that: The foundation pit safety monitoring model is: Among them, P j is the matching degree between the input fracture information set data and the jth fracture type, N j is the total number of historical fracture information set data corresponding to the jth fracture type, N0 is the total number of features of the input fracture information set data, N 同 is the total number of identical features between the feature data of the input fracture information set data and the historical fracture set data corresponding to the jth fracture type, α' l is the correlation weight between the feature data of the j-th fracture type and the l-th input fracture set data and the same feature in the historical fracture set data corresponding to the j-th fracture type, max(N j , N0) is the maximum value function.

7. A method for safety supervision of deep foundation pit construction of underground railway stations according to claim 6, characterized in that: The reliability analysis of foundation pit construction safety based on the foundation pit risk value specifically includes the following steps: Compare the foundation pit risk value with the preset threshold in the system; If the foundation pit risk value is greater than or equal to the preset threshold, the foundation pit has a greater risk and the safety reliability of the foundation pit is low; If the foundation pit risk value is less than the preset threshold, the foundation pit has a smaller risk and a higher safety reliability; Take measures to deal with low and high reliability respectively.

8. A method for safety supervision of deep foundation pit construction of underground railway stations according to claim 1, characterized in that: The specific measures taken for foundation pits with low reliability include the following steps: Use a mixing machine to proportion the concrete raw materials; Pour the well-proportioned concrete to the dangerous crack area; Maintain the poured concrete; The foundation pit with higher reliability specifically includes the following steps: The images of the normal crack area were collected continuously for one week; Repeat the above analysis operation on the collected image to obtain the width information, length information and depth information of the crack; Calculate the crack size information within one week based on the width information, length information and depth information; The crack size information before and after is calculated, and the expansion rate of the crack before and after is obtained by dividing the time difference before and after. Sum all the expansion rates and divide by the number to get the average rate of crack expansion; comparing the average rate of crack expansion with a second threshold; If the average rate of crack expansion is greater than or equal to the second threshold, the crack at that location is protected and reinforced; If the average rate of crack expansion is less than the second threshold, it is considered normal expansion and no measures are taken.

9. A safety supervision system for deep foundation pit construction of underground railway stations, used to implement a safety supervision method for deep foundation pit construction of underground railway stations as claimed in any one of claims 1 to 8, characterized in that: include: A shooting module, wherein the shooting module is used to shoot the concrete in the deep foundation pit of the underground railway station in real time using a high-definition shooting device to obtain an image of the concrete in the foundation pit; An image preprocessing module, wherein the image preprocessing module internally integrates a first image processing unit, a second image processing unit and a third image processing unit; A crack information extraction module, which is used to analyze the crack area in the preprocessed foundation pit concrete image and extract the length information, width information and depth information of the crack to form a crack information set; A foundation pit risk value acquisition module, which is used to retrieve a pre-set foundation pit safety monitoring model from a database, input a set of crack information into the foundation pit safety monitoring model, output crack types, and obtain a risk value of the foundation pit; A foundation pit reliability evaluation module is provided, wherein the foundation pit reliability evaluation module analyzes the reliability of foundation pit construction safety based on the foundation pit risk value.

10. A safety supervision system for deep foundation pit construction of underground railway stations according to claim 9, characterized in that: include: A first image processing unit, wherein the first image processing unit is used for image denoising; A second image processing unit, wherein the second image processing unit is used for image enhancement; A third image processing unit is used for image segmentation.

Images