A tunnel construction dynamic risk map generation method and system

Abstract

The application provides a tunnel construction dynamic risk map generation method and system, and belongs to the technical field of safety production. A BIM model and a GIS map are used to construct a tunnel three-dimensional base map; dynamic risk monitoring data of N dynamic risk monitoring points is acquired based on a real-time data detection system; the dynamic risk monitoring data is analyzed based on an improved analytic hierarchy process with comprehensive weights to obtain risk value calculation results; and the risk value calculation results are embedded into the tunnel three-dimensional base map to generate a visual dynamic risk map. The application comprehensively considers ahp weights, dynamic risk weights and adjustment coefficients, takes into account the scientific nature of experience and data, meets the risk assessment needs of different stages of tunnel construction, and adapts to the dynamic engineering scene of tunnel construction. The parameters of the tunnel construction dynamic risk map generation method are explicitly configured, the adjustment mode of the tunnel construction dynamic risk assessment model is simplified, and the problem that the risk assessment model cannot quickly adapt to working condition changes is solved.

Description

Technical Field

[0001] This invention belongs to the field of safety production technology, and in particular relates to a method and system for generating dynamic risk maps for tunnel construction. Background Technology

[0002] Tunnel construction is characterized by highly concealed geological conditions, dynamically changing construction conditions, and complex coupling of risk factors. Traditional static risk assessments for tunnel construction (such as a one-time risk list before construction) are difficult to adapt to the actual needs of the project. Dynamic risk maps for tunnel construction, by integrating real-time monitoring data, construction stages, environmental changes, and other multi-source information, transform abstract risk values ​​into a visualized, spatialized risk distribution map, providing support for construction safety, progress control, cost optimization, and decision-making. However, existing methods for generating dynamic risk maps for tunnel construction have the following problems: First, they often use fixed weights, which cannot adapt to the risk characteristics of different stages of tunnel construction; empirical weights are severely separated from field data weights, either relying too heavily on experience and deviating from actual field conditions, or focusing solely on data while ignoring engineering experience; second, dynamic risk assessment models are complex (such as deep learning and numerical simulation), requiring high computing power, making them difficult to deploy on-site, and model adjustments, especially parameter adjustments, are cumbersome, making it difficult for on-site personnel to quickly adapt to changes in working conditions. These problems affect the results of tunnel construction risk assessments, potentially leading to ineffective early warnings, impacting construction progress, and posing safety hazards. Summary of the Invention

[0003] To address the aforementioned problems in existing technologies, this invention proposes a method and system for generating dynamic risk maps for tunnel construction, which adapts to dynamic engineering scenarios in tunnel construction while simplifying model adjustment methods.

[0004] To achieve the above objectives, the present invention adopts the following technical solution: a method for generating a dynamic risk map for tunnel construction, comprising the following steps: S1: constructing a three-dimensional base map of the tunnel using a BIM model and a GIS map; S2: acquiring dynamic risk monitoring data of N dynamic risk monitoring points based on a real-time data detection system; the dynamic risk monitoring data includes the surrounding rock integrity index, groundwater seepage flow, lining strain value, convergence displacement rate, steel arch stress, toxic gas concentration, and grouting flow stability; S3: analyzing the dynamic risk monitoring data of one of the N dynamic risk monitoring points using a comprehensive weighted improved hierarchical analysis method to obtain the risk value calculation result; S4: repeating step S3 to obtain the risk value calculation results of the N dynamic risk monitoring points, embedding the risk value calculation results of the N dynamic risk monitoring points into the three-dimensional base map of the tunnel to generate a visualized dynamic risk map.

[0005] Furthermore, the real-time data detection system includes ground-penetrating radar, flow meter, strain sensor, displacement sensor, stress sensor, and gas sensor.

[0006] Further, step S3 specifically includes the following steps: S31: For a dynamic risk monitoring point, construct an a×b dimensional dynamic risk monitoring data original matrix; where a is the number of monitoring points of the dynamic risk monitoring point, and b is the dimension of the dynamic risk monitoring point; S32: Construct a first loop with 1 as the loop start value and step size, and b as the loop maximum value. For each loop of the first loop, extract the column data corresponding to that loop of the dynamic risk monitoring data original matrix, and calculate the mean and standard deviation of the column data; calculate the absolute difference between each data point in the column data and the mean. When the absolute difference is greater than k1 times the standard deviation, replace the value of the data point corresponding to the absolute difference with k2 times the mean; finally, obtain the preprocessed dynamic risk monitoring data original matrix; S33: Using 1 as the starting value and step size, and b as the maximum value, a second loop is constructed. For each iteration of the second loop, the corresponding column data of the preprocessed dynamic risk monitoring data original matrix for that loop is extracted, and the maximum and minimum values ​​of the column data are calculated. The absolute difference between each data point in the column data and the minimum value is calculated to obtain a first difference. The difference between the maximum and minimum values ​​is calculated to obtain a second difference. The ratio of the first difference to the second difference is calculated, and the ratio is used to replace the corresponding data point of the column data. Finally, a normalized dynamic risk monitoring data original matrix is ​​obtained. S34: Initialize a risk assessment index matrix with dimension b, and based on the risk assessment index matrix, normalize the normalized dynamic risk monitoring data original matrix to obtain a positive dynamic risk monitoring data original matrix. S35: Calculate the tunnel construction dynamic risk weight and adjustment coefficient. Based on the tunnel construction dynamic risk weight and the adjustment coefficient, the final weight is obtained. S36: Based on the final weight, calculate the risk value calculation result.

[0007] Further, step S34 includes the following steps: S341: Using 0 or 1 as the rule value, establish a risk assessment index matrix with dimension b corresponding to the dimension of the dynamic risk monitoring point; S342: Using 1 as the starting value and step size of the loop, and b as the maximum value of the loop, construct a third loop. For each loop of the third loop, determine whether the data value in the risk assessment index matrix corresponding to each loop is 0; S343: If the data value in the risk assessment index matrix corresponding to the loop is 0, then replace the column data corresponding to the loop in the normalized dynamic risk monitoring data original matrix with the absolute difference between the column data and 1. Otherwise, keep the column data corresponding to the loop in the original normalized dynamic risk monitoring data original matrix unchanged, thereby obtaining the positive dynamic risk monitoring data original matrix.

[0008] Further, step S35 includes the following steps: S351: Define an a×b dimensional probability distribution matrix p; construct a fourth loop with 1 as the loop start value and step size, and b as the loop maximum value; S352: For each loop in the fourth loop, calculate the sum of the column data of the original positive dynamic risk monitoring data matrix corresponding to that loop, denoted as the first sum value, and calculate the quotient of each data in the column data of the original positive dynamic risk monitoring data matrix with the first sum value, as the corresponding column data of the probability distribution matrix p; after completing the fourth loop, update the... S353: Initialize the 1×b-dimensional average information matrix e, using 1 as the starting value and step size of the loop, and b as the maximum value of the loop to construct the fifth loop; for each loop in the fifth loop, extract the column data corresponding to the current loop of the probability distribution matrix p, and assign it to a column vector e_col; S354: Calculate the dot product of the natural logarithm of the column vector e_col and the column vector, and sum the results to obtain the second sum; take the negative of the second sum and divide it by the natural logarithm of a to obtain the column data corresponding to the average information matrix e; complete the above steps. After the fifth cycle, update the average information matrix e; S355: Calculate the difference between 1 and the average information matrix e element by element, and record it as the difference matrix; calculate the difference between 1 and the average information matrix e element by element and sum them to obtain the third sum; divide the difference matrix by the third sum to obtain the dynamic risk weight of tunnel construction; S356: Obtain tunnel construction stage information and determine the adjustment coefficient based on the tunnel construction stage information; wherein when the tunnel construction stage information shows that the tunnel construction is in the excavation stage, the adjustment coefficient is set as the first adjustment coefficient; when the tunnel construction stage information shows that the tunnel construction is in the support stage, the adjustment coefficient is set as the second adjustment coefficient; when the tunnel construction stage information shows that the tunnel construction is in the lining stage, the adjustment coefficient is set as the third adjustment coefficient; S357: Perform weight allocation on the dynamic risk monitoring data based on the analytic hierarchy process to obtain the AHP weight; multiply the AHP weight by the adjustment coefficient to obtain the first sub-weight; calculate the difference between 1 and the adjustment coefficient and multiply it by the dynamic risk weight of tunnel construction to obtain the second sub-weight; finally, add the first sub-weight and the second sub-weight to obtain the final weight.

[0009] Further, step S36 includes the following steps: S361: using the repmat function to repeat the final weights a rows to match the dimension of the original matrix of the positive dynamic risk monitoring data; S362: multiplying the repeated final weights element by element with the original matrix of the positive dynamic risk monitoring data, and summing the results by row to obtain the risk value calculation result.

[0010] This invention also proposes a dynamic risk map generation system for tunnel construction, used to execute the aforementioned method for generating a dynamic risk map for tunnel construction. The system includes a tunnel 3D base map construction module, a dynamic risk monitoring data acquisition module, a data analysis module, and an embedding module. The dynamic risk monitoring data acquisition module is connected to the data analysis module, which is also connected to the embedding module. The embedding module is connected to the tunnel 3D base map construction module. The tunnel 3D base map construction module is used to construct a tunnel 3D base map using a BIM model and a GIS map. The dynamic risk monitoring data acquisition module is used to acquire dynamic risk monitoring data from N dynamic risk monitoring points. The data analysis module is used to analyze the dynamic risk monitoring data from the N dynamic risk monitoring points based on a comprehensive weighted improved analytic hierarchy process (AHP) to obtain risk value calculation results. The embedding module is used to embed the risk value calculation results into the tunnel 3D base map.

[0011] The beneficial technical effects of this invention compared with the prior art are as follows: (1) Taking into account the weight of AHP, dynamic risk weight and adjustment coefficient, and taking into account the scientific nature of experience and data, it is more in line with the risk assessment needs of different stages of tunnel construction and adapts to the dynamic engineering scenario of tunnel construction; (2) The parameters of the tunnel construction dynamic risk map generation method are explicitly configured, simplifying the adjustment method of the tunnel construction dynamic risk assessment model and solving the problem that the risk assessment model cannot quickly adapt to changes in working conditions. Attached Figure Description

[0012] To more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely exemplary, and those skilled in the art can derive other embodiments based on the provided drawings without creative effort.

[0013] Figure 1 This is a flowchart of a method for generating dynamic risk maps for tunnel construction according to the present invention; Figure 2 This is a simplified structural diagram of a tunnel construction dynamic risk map generation system according to the present invention. Detailed Implementation

[0014] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0015] The concepts involved in this application will first be described with reference to the accompanying drawings. It should be noted that the following descriptions of various concepts are only for the purpose of making the content of this application easier to understand and do not constitute a limitation on the scope of protection of this application; furthermore, the embodiments and features in the embodiments of this application can be combined with each other unless otherwise specified. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0016] Refer to the instruction manual. Figure 1 This invention proposes a method for generating dynamic risk maps for tunnel construction, comprising the following steps: S1: Constructing a three-dimensional base map of the tunnel using a BIM model and a GIS map; specifically, this can be achieved by first obtaining topographic images and surrounding environmental data along the tunnel route through aerial survey data, and then combining the tunnel design blueprint with BIM software (such as Revit) to draw the tunnel axis, construct the main structure (such as tunnel lining, entrance, etc.), and add auxiliary equipment (such as ventilation, lighting, drainage, and other key auxiliary components) to complete the BIM modeling; then importing the surrounding environmental data into GIS software (such as ArcGIS Pro, SuperMap) to generate a three-dimensional topographic base map; finally, exporting the BIM model to a GIS-compatible format (such as IFC or CityGML) and importing it into the GIS scene, adjusting the position of the BIM model to accurately match the GIS terrain and surrounding buildings, thereby completing the construction of the three-dimensional base map of the tunnel.

[0017] S2: A real-time data detection system based on a sensor network including ground-penetrating radar, flow meters, strain sensors, displacement sensors, stress sensors, and gas sensors acquires dynamic risk monitoring data from N dynamic risk monitoring points. This dynamic risk monitoring data includes the surrounding rock integrity index, groundwater seepage flow, lining strain value, convergence displacement rate, steel arch stress, toxic gas concentration, and grouting flow stability. The number of dynamic risk monitoring points N needs to be determined comprehensively based on the tunnel span, geological conditions, construction methods, and monitoring items.

[0018] S3: Based on the comprehensive weighted improved analytic hierarchy process, the dynamic risk monitoring data of one of the N dynamic risk monitoring points is analyzed to obtain the risk value calculation result.

[0019] S4: Repeat step S3 above to obtain the risk value calculation results of the N dynamic risk monitoring points, embed the risk value calculation results of the N dynamic risk monitoring points into the tunnel three-dimensional base map, and generate a visualized dynamic risk map.

[0020] This invention analyzes the dynamic risk monitoring data of one of the N dynamic risk monitoring points based on the comprehensive weighted improved analytic hierarchy process. Specifically, the analysis includes the following steps: S31: For a dynamic risk monitoring point, construct an a×b dimensional original matrix of dynamic risk monitoring data; where a is the number of monitoring points (e.g., 10 monitoring points can be set for each dynamic risk monitoring point), and b is the dimension of the dynamic risk monitoring point (e.g., for each monitoring point, dimensions such as surrounding rock integrity index, groundwater seepage flow, lining strain value, convergence displacement rate, steel arch stress, toxic gas concentration, and grouting flow stability can be set); S32: Construct a first loop with 1 as the loop start value and step size, and b as the loop maximum value. For each iteration of the first loop, extract the corresponding column data of the dynamic risk monitoring data original matrix for that loop, and calculate the mean and standard deviation of the column data; calculate the absolute difference between each data point in the column data and the mean. When the absolute difference is greater than k1 times the standard deviation, replace the value of the data point corresponding to the absolute difference with k. The mean is twice the value; finally, the preprocessed dynamic risk monitoring data original matrix is ​​obtained; S33: a second loop is constructed with 1 as the loop start value and step size, and b as the loop maximum value. For each loop of the second loop, the corresponding column data of the preprocessed dynamic risk monitoring data original matrix for that loop is extracted and the maximum and minimum values ​​of the column data are calculated. The absolute difference between each data point in the column data and the minimum value is calculated to obtain the first difference value. The difference between the maximum and minimum values ​​is calculated to obtain the second difference value. The ratio of the first difference value and the second difference value is calculated, and the ratio value is used to replace the corresponding data point of the column data; finally, the normalized dynamic risk monitoring data original matrix is ​​obtained; S34: the risk assessment index matrix with dimension b is initialized, and based on the risk assessment index matrix, the normalized dynamic risk monitoring data original matrix is ​​positively oriented to obtain the positively oriented dynamic risk monitoring data original matrix, thereby unifying the risk assessment standard; the above positive orientation also objectively improves the scalability of the risk assessment index matrix, which can thus play a beneficial role in simplifying the adjustment method of the tunnel construction dynamic risk assessment model; S35: Calculate the dynamic risk weight and adjustment coefficient for tunnel construction, and obtain the final weight based on the dynamic risk weight and adjustment coefficient for tunnel construction; S36: Calculate the risk value calculation result based on the final weight.

[0021] Step S34 includes the following steps: S341: Using 0 or 1 as the rule value, establish a risk assessment index matrix with dimension b corresponding to the dimension of the dynamic risk monitoring point; S342: Using 1 as the starting value and step size of the loop, and b as the maximum value of the loop, construct a third loop. For each loop of the third loop, determine whether the data value in the risk assessment index matrix corresponding to each loop is 0; S343: If the data value in the risk assessment index matrix corresponding to the loop is 0, replace the column data corresponding to the loop in the normalized dynamic risk monitoring data original matrix with the absolute difference between the column data and 1. Otherwise, keep the column data corresponding to the loop in the original normalized dynamic risk monitoring data original matrix unchanged, thereby obtaining the positive dynamic risk monitoring data original matrix.

[0022] Step S35 includes the following steps: S351: Define an a×b dimensional probability distribution matrix p; construct a fourth loop with 1 as the loop start value and step size, and b as the loop maximum value; S352: For each loop in the fourth loop, calculate the sum of the column data of the original positive dynamic risk monitoring data matrix corresponding to that loop, denoted as the first sum value, and calculate the quotient of each data in the column data of the original positive dynamic risk monitoring data matrix with the first sum value, as the corresponding column data of the probability distribution matrix p; update the probability distribution matrix p after completing the fourth loop; S353: Initialization S354: Calculate the dot product of the natural logarithm of the column vector e with the column vector p, and sum the results to obtain the second sum. Then, take the negative of the second sum and divide it by the natural logarithm of a to obtain the corresponding column data of the average information matrix e. After completing the fifth loop, update the average information matrix e. S355: Calculate element-wise... The difference between 1 and the average information matrix e is denoted as the difference matrix; the difference between 1 and the average information matrix e is calculated element by element and summed to obtain the third sum; the difference matrix is ​​divided by the third sum to obtain the dynamic risk weight of tunnel construction; S356: Obtain tunnel construction stage information, and determine the adjustment coefficient based on the tunnel construction stage information. It can be understood that the above adjustment coefficient is a positive number less than 1; wherein when the tunnel construction stage information shows that the tunnel construction is in the excavation stage, the adjustment coefficient is set as the first adjustment coefficient; when the tunnel construction stage information shows that the tunnel construction is in the support stage, the adjustment coefficient is set as the second adjustment coefficient. The first adjustment coefficient is set as the second adjustment coefficient; when the tunnel construction stage information shows that the tunnel construction is in the lining stage, the third adjustment coefficient is set; S357: The dynamic risk monitoring data is weighted based on the analytic hierarchy process (AHP) to obtain the AHP weight (that is, the dynamic risk monitoring data can be pre-weighted using empirical values); the AHP weight is multiplied by the adjustment coefficient to obtain the first sub-weight, the difference between 1 and the adjustment coefficient is calculated and multiplied by the tunnel construction dynamic risk weight to obtain the second sub-weight, and finally the first sub-weight and the second sub-weight are added to obtain the final weight. By matching the adjustment coefficient with the tunnel construction stage, it can better reflect the dynamic engineering scenario. For example, in the construction stage, the geological uncertainty is high, the construction disturbance is large, and sudden risks such as collapse / water inrush are prone to occur. At this time, the AHP weight can be the main factor; while in the lining stage or the later stage of construction, the tunnel structure is relatively stable, and the tunnel construction dynamic risk weight should be the main factor.Meanwhile, the construction of the aforementioned risk assessment index matrix and the setting of multiple weights are all extracted from the hidden code logic and configured in a directly modifiable form. This simplifies the adjustment method of the dynamic risk assessment model for tunnel construction and solves the problem that the risk assessment model cannot quickly adapt to changes in working conditions during tunnel construction.

[0023] Step S36 includes the following steps: S361: Use the repmat function to repeat the final weights a rows to match the dimension of the original matrix of the positive dynamic risk monitoring data; S362: Multiply the repeated final weights element by element with the original matrix of the positive dynamic risk monitoring data, and sum the results of the multiplication by row to obtain the risk value calculation result.

[0024] Refer to the instruction manual. Figure 2 This invention also proposes a dynamic risk map generation system for tunnel construction, used to execute the aforementioned method for generating a dynamic risk map for tunnel construction. The system includes a tunnel 3D base map construction module, a dynamic risk monitoring data acquisition module, a data analysis module, and an embedding module. The dynamic risk monitoring data acquisition module is connected to the data analysis module, which in turn is connected to the embedding module, which is also connected to the tunnel 3D base map construction module. The tunnel 3D base map construction module is used to construct a tunnel 3D base map using a BIM model and a GIS map. The dynamic risk monitoring data acquisition module is used to acquire dynamic risk monitoring data from N dynamic risk monitoring points. The data analysis module is used to analyze the dynamic risk monitoring data from the N dynamic risk monitoring points based on a comprehensive weighted improved hierarchical analysis method to obtain risk value calculation results. The embedding module is used to embed the risk value calculation results into the tunnel 3D base map. By generating a dynamic risk map, abstract risk values ​​can be quickly mapped to specific locations within the tunnel, high-risk areas can be quickly identified, and the correlation between risk points can be analyzed to provide an intuitive basis for developing targeted response plans, thereby improving management efficiency.

[0025] The embodiments and / or implementation methods described above are merely preferred embodiments and / or implementation methods for implementing the technology of the present invention, and are not intended to limit the implementation methods of the technology of the present invention in any way. Any person skilled in the art may make some modifications or alterations to other equivalent embodiments without departing from the scope of the technical means disclosed in the present invention, but these should still be regarded as the technology or embodiments that are substantially the same as the present invention.

[0026] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. The above descriptions are only preferred embodiments of this application. It should be noted that due to the limitations of written expression, while there are objectively infinite specific structures, those skilled in the art can make several improvements, modifications, or changes without departing from the principles of this application, and can also combine the above technical features in an appropriate manner. These improvements, modifications, changes, or combinations, or the direct application of the inventive concept and technical solution to other situations without modification, should all be considered within the scope of protection of this application.

Claims

1. A method for generating a dynamic risk map for tunnel construction, characterized in that, Includes the following steps: S1: Construct a 3D base map of the tunnel using BIM model and GIS map; S2: Based on the real-time data detection system, acquire dynamic risk monitoring data of N dynamic risk monitoring points; the dynamic risk monitoring data includes surrounding rock integrity index, groundwater seepage flow, lining strain value, convergence displacement rate, steel arch stress, toxic gas concentration and grouting flow stability. S3: Based on the comprehensive weighted improved analytic hierarchy process, analyze the dynamic risk monitoring data of one of the N dynamic risk monitoring points to obtain the risk value calculation result; S4: Repeat step S3 above to obtain the risk value calculation results of the N dynamic risk monitoring points, embed the risk value calculation results of the N dynamic risk monitoring points into the tunnel three-dimensional base map, and generate a visualized dynamic risk map.

2. The method for generating a dynamic risk map for tunnel construction according to claim 1, characterized in that, The real-time data detection system includes ground-penetrating radar, flow meter, strain sensor, displacement sensor, stress sensor, and gas sensor.

3. The method for generating a dynamic risk map for tunnel construction according to claim 1, characterized in that, Step S3 specifically includes the following steps: S31: For a dynamic risk monitoring point, construct an a×b dimensional dynamic risk monitoring data original matrix; where a is the number of monitoring points of the dynamic risk monitoring point, and b is the dimension of the dynamic risk monitoring point. S32: Construct a first loop with 1 as the loop start value and step size, and b as the loop maximum value. For each loop of the first loop, extract the corresponding column data of the original matrix of the dynamic risk monitoring data for that loop, and calculate the mean and standard deviation of the column data. Calculate the absolute difference between each data point in the column data and the mean. When the absolute difference is greater than k1 times the mean squared error, replace the value of the data point corresponding to the absolute difference with k2 times the mean. Finally, the original matrix of preprocessed dynamic risk monitoring data is obtained; S33: Construct a second loop with 1 as the loop start value and step size, and b as the loop maximum value. For each loop of the second loop, extract the corresponding column data of the preprocessed dynamic risk monitoring data original matrix for that loop and calculate the maximum and minimum values ​​of the column data. Calculate the absolute difference between each data point in the column data and the minimum value to obtain a first difference value. Calculate the difference between the maximum and minimum values ​​to obtain a second difference value. Calculate the ratio of the first difference value to the second difference value and replace the corresponding data point of the column data with the ratio value. Finally, the normalized dynamic risk monitoring data original matrix is ​​obtained; S34: Initialize a risk assessment index matrix with dimension b, and based on the risk assessment index matrix, normalize the original matrix of the normalized dynamic risk monitoring data to obtain a normalized original matrix of the dynamic risk monitoring data. S35: Calculate the dynamic risk weight and adjustment coefficient for tunnel construction, and obtain the final weight based on the dynamic risk weight and adjustment coefficient for tunnel construction; S36: Calculate the risk value result based on the final weight.

4. The method for generating a dynamic risk map for tunnel construction according to claim 3, characterized in that, Step S34 includes the following steps: S341: Using 0 or 1 as the rule value, establish a risk assessment index matrix with dimension b corresponding to the dimension of the dynamic risk monitoring point; S342: Construct a third loop with 1 as the loop start value and step size, and b as the loop maximum value. For each loop of the third loop, determine whether the data value in the risk assessment index matrix corresponding to each loop is 0. S343: If the data value in the risk assessment index matrix corresponding to the cycle is 0, then the column data corresponding to the cycle in the original normalized dynamic risk monitoring data matrix is ​​replaced with the absolute difference between the column data and 1. Otherwise, the column data corresponding to the cycle in the original normalized dynamic risk monitoring data matrix remains unchanged, thereby obtaining the original positive dynamic risk monitoring data matrix.

5. The method for generating a dynamic risk map for tunnel construction according to claim 4, characterized in that, Step S35 includes the following steps: S351: Define an a×b dimensional probability distribution matrix p; construct a fourth loop with 1 as the loop start value and step size, where b is the loop maximum value; S352: For each cycle in the fourth cycle, calculate the sum of the column data of the original matrix of positive dynamic risk monitoring data corresponding to that cycle, and record it as the first sum value. Also calculate the quotient of each data in the column data of the original matrix of positive dynamic risk monitoring data with the first sum value, and use it as the corresponding column data of the probability distribution matrix p. After completing the fourth loop, update the probability distribution matrix p; S353: Initialize the 1×b-dimensional average information matrix e, and construct the fifth loop with 1 as the loop start value and step size, where b is the loop maximum value; For each iteration in the fifth loop, extract the column data corresponding to that iteration of the probability distribution matrix p and assign it to a column vector e_col; S354: Calculate the dot product of the natural logarithm of the column vector e_col and the column vector, and sum them to obtain the second sum value; The negative of the second sum is divided by the natural logarithm of a to obtain the corresponding column data of the average information matrix e; After completing the fifth cycle, update the average information matrix e; S355: Calculate the difference between 1 and the average information matrix e element by element, and denote it as the difference matrix; calculate the difference between 1 and the average information matrix e element by element and sum them to obtain the third sum value; divide the difference matrix by the third sum value to obtain the dynamic risk weight of tunnel construction. S356: Obtain tunnel construction stage information and determine adjustment coefficients based on the tunnel construction stage information; wherein when the tunnel construction stage information shows that the tunnel construction is in the excavation stage, the adjustment coefficient is set as the first adjustment coefficient; when the tunnel construction stage information shows that the tunnel construction is in the support stage, the adjustment coefficient is set as the second adjustment coefficient; when the tunnel construction stage information shows that the tunnel construction is in the lining stage, the adjustment coefficient is set as the third adjustment coefficient. S357: The dynamic risk monitoring data is weighted based on the analytic hierarchy process (AHP) to obtain the AHP weights; the AHP weights are multiplied by the adjustment coefficients to obtain the first sub-weights; the difference between 1 and the adjustment coefficients is calculated and multiplied by the dynamic risk weights of tunnel construction to obtain the second sub-weights; finally, the first sub-weights and the second sub-weights are added together to obtain the final weights.

6. The method for generating a dynamic risk map for tunnel construction according to claim 5, characterized in that, Step S36 includes the following steps: S361: Use the repmat function to repeat the final weights a rows to match the dimension of the original matrix of the positive dynamic risk monitoring data; S362: Multiply the final weight after repetition with the original matrix of the positive dynamic risk monitoring data element by element, and sum the results of the multiplication row by row to obtain the risk value calculation result.

7. A tunnel construction dynamic risk map generation system, used to execute the tunnel construction dynamic risk map generation method as described in any one of claims 1-6, characterized in that, The tunnel construction dynamic risk map generation system includes a tunnel 3D base map construction module, a dynamic risk monitoring data acquisition module, a data analysis module, and an embedding module. The dynamic risk monitoring data acquisition module is connected to the data analysis module, the data analysis module is connected to the embedding module, and the embedding module is connected to the tunnel 3D base map construction module. The tunnel 3D base map construction module is used to construct a tunnel 3D base map using BIM model and GIS map. The dynamic risk monitoring data acquisition module is used to acquire dynamic risk monitoring data from N dynamic risk monitoring points; The data analysis module is used to analyze the dynamic risk monitoring data of the N dynamic risk monitoring points based on the comprehensive weighted improved analytic hierarchy process to obtain the risk value calculation results; The embedding module is used to embed the risk value calculation results into the tunnel's three-dimensional base map.

Images