Tunnel construction risk assessment method based on ANP and matter-element normal cloud model

Abstract

The invention discloses a tunnel construction risk assessment method based on ANP and a matter-element normal cloud model, and relates to the technical field of construction risk assessment. The tunnel construction risk assessment method based on ANP and a matter-element normal cloud model mainly comprises the following steps: obtaining a tunnel construction risk assessment index system in the cold and cold mountainous area according to main risk factors influencing tunnel construction in the cold and cold mountainous area, and obtaining each index weight by using a network analytic hierarchy process; and performing high-cold mountain area tunnel construction risk assessment by using a matter-element theory and a normal cloud model to obtain an overall result of high-cold mountain area tunnel construction risk assessment. By implementing the tunnel construction risk assessment method based on ANP and matter-element normal cloud model provided by the invention, the accuracy and practicability of tunnel construction risk assessment can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of construction risk assessment, and more specifically to a tunnel construction risk assessment method based on ANP and matter-element normal cloud model. Background Art

[0002] Tunnel construction in high-cold mountainous areas is an extremely challenging engineering task. The construction environment is harsh, the temperature is extremely low, and it is often accompanied by extreme weather conditions such as strong winds and heavy snow. These factors bring great uncertainty and risks to tunnel construction. In high-cold mountainous areas, tunnel excavation may encounter a variety of complex geological conditions such as frozen soil, hard rock, and groundwater. These geological factors not only increase the difficulty of construction, but may also lead to safety accidents such as tunnel collapse and water gushing, which seriously threaten the lives of construction workers and the smooth progress of engineering projects.

[0003] Traditional tunnel construction risk assessment methods, such as expert scoring method and analytic hierarchy process, can reflect the size of construction risks to a certain extent, but most of these methods rely on the subjective judgment and experience accumulation of experts, lacking objectivity and accuracy. Especially in the special environment of high-altitude and cold mountainous areas, the complexity and uncertainty of construction risks are more prominent, and traditional risk assessment methods are often difficult to comprehensively and accurately assess construction risks.

[0004] In recent years, with the development of system engineering and risk management theory, some new risk assessment methods have been gradually introduced into the field of tunnel construction. Among them, the analytic network process (ANP), as an assessment method that considers the mutual influence relationship between factors, can more comprehensively reflect the actual situation of construction risks. However, the ANP method still has certain limitations in dealing with risk ambiguity and randomness. Summary of the invention

[0005] The purpose of the present invention is to provide a tunnel construction risk assessment method based on ANP and matter-element normal cloud model, which can improve the accuracy and practicability of tunnel construction risk assessment.

[0006] The present invention provides a tunnel construction risk assessment method based on ANP and matter-element normal cloud model, comprising the following steps: S1: obtaining a risk assessment index system for tunnel construction in high-cold mountainous areas according to main risk factors affecting tunnel construction in high-cold mountainous areas, wherein the risk assessment index system for tunnel construction in high-cold mountainous areas includes at least one criterion, and the criterion includes at least one sub-criterion; S2: obtaining weights of various indicators by using the network analytic hierarchy process according to the risk assessment index system for tunnel construction in high-cold mountainous areas; S3: conducting risk assessment of tunnel construction in high-cold mountainous areas by using matter-element theory and normal cloud model according to the risk assessment index system for tunnel construction in high-cold mountainous areas and the weights of various indicators, and obtaining an overall result of risk assessment of tunnel construction in high-cold mountainous areas.

[0007] Furthermore, the above-mentioned high-altitude and cold mountainous area tunnel construction risk assessment index system includes the following criteria: geological factors, groundwater factors, design and construction factors, organizational and management factors, and natural environment factors; geological factors include the following sub-criteria: surrounding rock grade, broken zone, unfavorable geology, bias angle, and burial depth ratio; groundwater factors include the following sub-criteria: groundwater level and groundwater inflow; design and construction factors include the following sub-criteria: stratum reinforcement method, excavation method, excavation span, support method, blasting disturbance, and monitoring and measurement; organizational and management factors include at least the following sub-criteria: construction management; natural environment factors include at least the following sub-criteria: annual average temperature, air oxygen content, and annual average rainfall.

[0008] Furthermore, step S2 specifically includes: S21: Based on the risk assessment index system for tunnel construction in high-cold mountainous areas, using the expert questionnaire method, the influence relationship between sub-criteria is obtained; S22: Based on the influence relationship between the sub-criteria, a judgment matrix is ​​obtained using the 1-9 scaling method; S23: Based on the judgment matrix, the network hierarchy analysis method is used to calculate the global weights of all sub-criteria to obtain the weights of each indicator.

[0009] Furthermore, step S23 specifically includes: S231: obtaining a supermatrix based on the judgment matrix; S232: constructing a new judgment matrix with each element group as a sub-criterion and comparing the importance of the element groups two by two to obtain a weighted matrix, and obtaining a weighted supermatrix based on the weighted matrix and the supermatrix; S233: infinitely multiplying the weighted supermatrix by itself until the matrix becomes stable and no longer changes, thereby obtaining the weights of each indicator.

[0010] Furthermore, step S3 specifically includes: S31: performing dimensionless processing on the measured values ​​of the risk assessment index system for tunnel construction in high-cold mountainous areas to obtain dimensionless values ​​of evaluation indicators; S32: determining the standard cloud of evaluation indicators based on the dimensionless values ​​of evaluation indicators using the matter-element theory and the normal cloud model; S33: obtaining the correlation between each evaluation indicator based on the standard cloud; S34: obtaining the overall result of the risk assessment of tunnel construction in high-cold mountainous areas based on the correlation between each evaluation indicator.

[0011] Further, step S32 specifically includes: according to the dimensionless value of the evaluation index, using the matter-element theory and the normal cloud model, determining the standard cloud of the evaluation index, such as the formula: , , , in, , , They represent the expectation, entropy, and super entropy of the standard cloud of the evaluation index respectively; , It represents the minimum and maximum values ​​of the dimensionless value of the evaluation index and the evaluation standard interval; Is a constant.

[0012] Further, step S33 specifically includes: according to the standard cloud of the evaluation indicators, obtaining the correlation degree of each evaluation indicator, such as the formula: , in, is the correlation degree of each evaluation index, Cloud droplets representing the normal cloud model, For For expectations, is a normal random number with standard deviation .

[0013] Further, step S34 specifically includes: according to the correlation degree of each evaluation index, the overall result of the risk assessment of tunnel construction in the high-cold mountainous area is obtained, such as the formula: , , in, For the indicators to be evaluated about the level The comprehensive correlation of For the The comprehensive weight of the indicators, K j ( v i ) is the Indicators about The correlation of the rating levels, This is the overall result of the risk assessment for tunnel construction in high-altitude mountainous areas.

[0014] Furthermore, the above-mentioned tunnel construction risk assessment method based on ANP and matter-element normal cloud model also includes: dynamic analysis of potential risks existing in the tunnel construction process in high-altitude mountainous areas, specifically including: real-time monitoring and data collection of key parameters in the tunnel construction process, using steps S1-S3 to conduct risk assessment, by comparing historical data and current status, identifying risk change trends, and timely warning of potential risks; according to the assessment results, formulating corresponding risk response strategies and measures; adjusting risk assessment models and parameters according to construction progress and changes in the external environment.

[0015] The present invention also provides a computer program product, comprising a computer program, which, when executed by a processor, implements the steps of the above-mentioned tunnel construction risk assessment method based on ANP and matter-element normal cloud model.

[0016] The tunnel construction risk assessment method based on ANP and matter-element normal cloud model provided by the present invention has the following beneficial effects: The present invention identifies and constructs a risk assessment index system covering the entire process of tunnel construction in high-cold mountainous areas. The system comprehensively considers multiple dimensions such as geological conditions, climatic conditions, construction technology, and management factors to ensure the comprehensiveness of risk assessment. The network analytic hierarchy process (ANP) is used to deeply analyze the mutual influence relationship among various risk indicators and determine the weight distribution of various risk factors to overcome the limitations of the independence assumption of risk factors in traditional assessment methods and achieve the dynamic and accuracy of risk assessment. The matter-element normal cloud model is used as an effective tool for dealing with ambiguity and randomness, which can comprehensively consider the ambiguity and randomness of risks, and realize the dual description of risk probability and ambiguity through the generation and aggregation of cloud droplets, thereby improving the accuracy and reliability of risk assessment. Based on the matter-element theory, the actual value of the risk indicator is converted into cloud droplets in the normal cloud model, and the expectation, entropy and hyperparameters of the cloud droplets are calculated. Entropy is used to accurately describe the fuzziness and randomness of risks, and a cloud model that can reflect the risk status of tunnel construction in high-cold mountainous areas is constructed; the normal cloud model is combined to calculate the membership of each risk indicator at different risk levels, and the weights determined by ANP are combined to evaluate the overall risk level of tunnel construction in high-cold mountainous areas; by constructing a comprehensive risk assessment indicator system, the ANP method is used to construct a network hierarchy of construction risks, the mutual influence relationship between risk factors is analyzed, and the matter-element normal cloud model is introduced to quantitatively evaluate risks, accurately describing the fuzziness and randomness of risks, and realizing a comprehensive, dynamic and accurate assessment of the risks of tunnel construction in high-cold mountainous areas; this method not only improves the accuracy and practicality of risk assessment, but also provides a strong scientific basis and technical support for the safety management and decision-making of tunnel construction in high-cold mountainous areas, effectively reducing construction risks and ensuring the smooth progress of engineering projects. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The present invention will be further described below with reference to the accompanying drawings and embodiments, in which: Figure 1 It is a flow chart of a tunnel construction risk assessment method based on ANP and matter-element normal cloud model provided by the present invention; Figure 2 It is a schematic diagram of a tunnel construction risk assessment method based on ANP and matter-element normal cloud model provided by the present invention; Figure 3 It is a schematic diagram of the ANP (analytic network process) classical structural model provided by the present invention. DETAILED DESCRIPTION

[0018] In order to have a clearer understanding of the technical features, purposes and effects of the present invention, specific embodiments of the present invention are now described in detail with reference to the accompanying drawings.

[0019] Figure 1 A schematic diagram of a tunnel construction risk assessment method based on ANP and matter-element normal cloud model in this embodiment is shown. In this embodiment, the tunnel construction risk assessment method based on ANP and matter-element normal cloud model includes the following steps: S1: Based on the main risk factors affecting the construction of tunnels in high-cold mountainous areas, a risk assessment index system for tunnel construction in high-cold mountainous areas is obtained. The risk assessment index system for tunnel construction in high-cold mountainous areas includes at least one criterion, and the criterion includes at least one sub-criterion; In an exemplary embodiment, the risk assessment index system for tunnel construction in high-cold mountainous areas includes the following criteria: geological factors, groundwater factors, design and construction factors, organizational and management factors, and natural environmental factors; geological factors include the following sub-criteria: surrounding rock grade, fracture zone, unfavorable geology, bias angle, and burial depth ratio; groundwater factors include the following sub-criteria: groundwater level and groundwater inflow; design and construction factors include the following sub-criteria: stratum reinforcement method, excavation method, excavation span, support method, blasting disturbance, and monitoring measurement; organizational and management factors include at least the following sub-criteria: construction management; natural environmental factors include at least the following sub-criteria: annual average temperature, air oxygen content, and annual average rainfall; S2: Based on the risk assessment index system for tunnel construction in high-cold mountainous areas, the weight of each index is obtained using the analytic network hierarchy process; In an exemplary embodiment, step S2 specifically includes: S21: Based on the risk assessment index system for tunnel construction in high-cold mountainous areas, the influence relationship between sub-criteria is obtained using the expert questionnaire method; S22: According to the influence relationship between the sub-criteria, the judgment matrix is ​​obtained using the 1-9 scaling method; S23: According to the judgment matrix, the network analytic hierarchy process is used to calculate the global weights of all sub-criteria and obtain the weights of each indicator; In an exemplary embodiment, step S23 specifically includes: S231: Obtain a supermatrix according to the judgment matrix; In an exemplary embodiment, step S231 specifically includes: obtaining a super matrix according to the judgment matrix, such as formula: , , in, It is The element group The weight vector matrix of groups of elements; Indicates the The first element of the group The element is used as the second criterion in the judgment matrix The normalized eigenvector elements; is the number of element groups; S232: taking each element group as a sub-criterion and comparing the importance of the element groups two by two to construct a new judgment matrix, obtaining a weighted matrix, and obtaining a weighted super-matrix according to the weighted matrix and the super-matrix; In an exemplary embodiment, step S232 specifically includes: taking each element group as a sub-criterion, comparing the importance of the element groups two by two to construct a new judgment matrix, obtaining a weighted matrix, and obtaining a weighted super-matrix according to the weighted matrix and the super-matrix, such as formula: , , in, is the weighting matrix, is the first normalized vector in the newly constructed judgment matrix Row and Column elements; is the weighted supermatrix; S233: infinitely multiply the weighted supermatrix by itself until the matrix becomes stable and no longer changes, and obtain the weight of each indicator; As an exemplary embodiment, in step S233, it is assumed that ,but Reflects the elements For Elements One-step advantage, element For Elements The dominance of We get the second-step advantage ;when When , we can get the limit supermatrix; the limit supermatrix is ​​the weighted supermatrix Infinitely multiply by itself until the matrix becomes stable and no longer changes. At this time, the column vector of the matrix is ​​the global weight of the element; S3: Based on the risk assessment index system of tunnel construction in high-cold mountainous areas and the weights of each index, the risk assessment of tunnel construction in high-cold mountainous areas is carried out using matter-element theory and normal cloud model to obtain the overall result of risk assessment of tunnel construction in high-cold mountainous areas; In an exemplary embodiment, step S3 specifically includes: S31: Dimensionless processing is performed on the measured values ​​of the risk assessment index system for tunnel construction in high-cold mountainous areas to obtain dimensionless values ​​of the evaluation indexes; As an exemplary embodiment, in step S31, each evaluation index is dimensionless processed so that the dimension of each index is between [0, 1], so that each index is directly comparable before evaluation; S32: According to the dimensionless value of the evaluation index, the standard cloud of the evaluation index is determined by using the matter-element theory and the normal cloud model; In an exemplary embodiment, step S32 specifically includes: according to the dimensionless value of the evaluation index, using the matter-element theory and the normal cloud model, determining the standard cloud of the evaluation index, such as the formula: , , , in, , , They represent the expectation, entropy, and super entropy of the standard cloud of the evaluation index respectively; , It represents the minimum and maximum values ​​of the dimensionless value of the evaluation index and the evaluation standard interval; is a constant; As an exemplary embodiment, in step S32, according to the 3En rule of normal cloud, the standard cloud of the high-cold mountain tunnel construction risk assessment index system is determined according to the conversion formula of cloud parameters; S33: Obtaining the correlation degree of each evaluation indicator according to the standard cloud of the evaluation indicators; In an exemplary embodiment, step S33 specifically includes: obtaining the correlation degree of each evaluation indicator according to the standard cloud of the evaluation indicator, such as the formula: , in, is the correlation degree of each evaluation index, Cloud droplets representing the normal cloud model, For For expectations, is a normal random number with standard deviation; It should be noted that since the correlation of the cloud calculated by the above formula is random, it is necessary to weaken its influence through multiple operations and take the median to obtain the correlation of each evaluation index; S34: According to the correlation of each evaluation index, the overall result of the risk assessment of tunnel construction in high-cold mountainous area is obtained; In an exemplary embodiment, step S34 specifically includes: obtaining the overall result of the risk assessment of tunnel construction in high-cold mountainous areas according to the correlation of each evaluation index, such as the formula: , , in, For the indicators to be evaluated about the level The comprehensive correlation of For the The comprehensive weight of the indicators, K j ( v i ) is the Indicators about The correlation of the rating levels, This is the overall result of the risk assessment for tunnel construction in high-altitude mountainous areas.

[0020] In an exemplary embodiment, the above-mentioned tunnel construction risk assessment method based on ANP and matter-element normal cloud model also includes: dynamic analysis of potential risks existing in the tunnel construction process in high-altitude mountainous areas, specifically including: real-time monitoring and data collection of key parameters in the tunnel construction process, using steps S1-S3 to conduct risk assessment, by comparing historical data and current status, identifying risk change trends, and timely warning of potential risks; according to the assessment results, formulating corresponding risk response strategies and measures; adjusting risk assessment models and parameters according to construction progress and changes in the external environment.

[0021] In some embodiments, the above-mentioned tunnel construction risk assessment method based on ANP and matter-element normal cloud model can also be implemented in the following manner.

[0022] like Figure 2 FIG. 1 is a schematic diagram of a tunnel construction risk assessment method based on ANP and matter-element normal cloud model in this embodiment; in this embodiment, the tunnel construction risk assessment method based on ANP and matter-element normal cloud model includes the following steps: Step 1: Determine the risk assessment index system for tunnel construction in high-altitude and cold mountainous areas: After conducting an in-depth study of historical cases of tunnel construction in high-cold mountainous areas and collecting and analyzing various risk events during the construction process, based on the survey results, expert interviews, literature reviews, on-site inspections and other methods were used to systematically identify the main risk factors affecting tunnel construction in high-cold mountainous areas; these risk factors cover multiple dimensions such as natural environment, engineering technology, and management organization; the identified risk factors are classified according to their nature and scope of influence, such as geological factors, groundwater factors, design and construction factors, organizational and management factors, natural environment factors, etc., and further refined into specific risk factors to provide a clear framework for subsequent evaluation; the final established high-cold mountainous area tunnel construction risk assessment system is shown in Table 1: Table 1: Risk assessment index system for tunnel construction in high-cold mountainous areas

[0023] Step 2: Determine the weights of each indicator in the risk assessment system for tunnel construction in high-cold mountainous areas: Use ANP (analytic network method) to determine the weights of each indicator in the risk assessment system for tunnel construction in high-cold mountainous areas; 1. ANP Overview: ANP (Analytical Network Process) is an improvement of AHP (Analytical Hierarchy Process), which solves the problem of weight calculation when there is an interdependent influence relationship between indicators; the classic structural model of the analytical network method is as follows Figure 3 As shown in the figure, the classic structural model of network analysis method consists of control layer and network layer. The control layer includes decision-making objectives and several criteria, and each criterion is independent of each other and does not affect each other. The network layer includes all element groups controlled by the control layer, which form an influence relationship network. Specifically, there are three types of influence relationships: mutual influence between two element groups, unidirectional influence of one element group on another element group, and mutual influence between elements within an element group. Determine the criteria, elements and element groups, and clarify the influence relationship between elements and element groups. Assume that there are three element groups , , , the composition of each element group is shown in Table 2: Table 2: Risk assessment indicator system

[0024] The influence relationship between elements is generally determined by experts, and the specific form is shown in Table 3: Table 3: Influence relationship table

[0025] In Table 3, 0 means that there is no influence relationship between the two elements, and 1 means that there is an influence relationship between the two elements; among them, an element has no influence on itself by default, that is, - (row-column), - ··· - ··· - The default value is 0 everywhere; the influence relationship is from row to column. For example, if - At 1, - If it is 0, it means right It has an impact, but No impact ; When multiple experts score to determine the influence relationship between elements, if more than half of the experts believe that there is an influence relationship, then the influence relationship is retained (1→1), otherwise it is considered that there is no influence relationship (1→0); Assuming that there is only one main criterion, the network layer has Element Group ··· , element group The elements in are denoted as ··· ; By element group An element in As a secondary criterion, the element group All impacts The elements of are compared pairwise, and the judgment matrix is ​​constructed using the 1-9 scaling method (as shown in Table 4). Then, the normalized eigenvector is calculated using the eigenroot method, that is, the weight vector of the AHP judgment matrix is ​​calculated. The judgment matrix is ​​shown in Table 5. Table 4: 1-9 scale

[0026] Table 5: is the judgment matrix of the sub-accuracy test

[0027] In Table 5, , , Meet the criteria of the 1-9 scale; assume Elements in the group , , right There is an influence relationship, building based on Sub-criteria The judgment matrix under the element group, after scoring according to the 1-9 scale method, is shown in Table 6; Table 6: Sub-criteria Judgment matrix under element group

[0028] Among them, the normalized feature vector calculation process is shown in Table 7; Table 7: Normalized eigenvector calculation process

[0029] After obtaining the normalized eigenvector, the judgment matrix needs to be checked for consistency. The formula is shown in formula (1); (1) In formula (1), is the maximum eigenvalue of the judgment matrix, To determine the matrix order, is the average random consistency index, and the values ​​are shown in Table 8; is the consistency ratio, if <0.1, the consistency of the judgment matrix is ​​acceptable, otherwise it needs to be corrected; Table 8: Average random consistency index

[0030] by Sub-criteria Take the judgment matrix under the element group as an example, ≈3.0536, then =[(3.0536-3) / (3-1)] / 0.52≈0.0515<0.1, the consistency of the judgment matrix is ​​acceptable; according to the above logic, the judgment matrices of all element groups with all elements as sub-criteria are constructed respectively, but the elements in the element group that do not affect the sub-criteria elements do not participate in the construction of the judgment matrix, and all judgment matrices must pass the consistency test; the element group All elements in the element group The normalized feature vectors obtained by constructing the judgment matrix are arranged and combined to obtain the weight vector matrix , as shown in formula (2); (2) in, The column vector of An element in As a secondary criterion, use element groups The normalized eigenvector finally obtained after constructing the judgment matrix of the elements that affect the element; Characterized Element Pairs The degree of influence of the element group; for all Repeat the weight vector matrix ( and is an integer), we can get the super matrix , as shown in formula (3); (3) in, Each column of is the element in all element groups for a certain element The combination of the weight vectors of influence; among them, the influence element The element group, the weight vector sum is 1, there is no influencing element The element group where the element is located has a weight vector of 0; As the secondary criterion, the importance of element groups is compared pairwise, and the judgment matrix is ​​constructed as shown in Table 9, and the normalized eigenvector is calculated; Table 9: is the judgment matrix of the sub-accuracy test

[0031] In Table 9, , , Meet the criteria of the 1-9 scale; if an element group does not affect , then the corresponding sorting vector component is 0, thus obtaining the weighted matrix , as shown in formula (4); (4) Supermatrix Using weighting matrix Weighted, get the weighted super matrix , as shown in formula (5); (5) set up ,but Reflects the elements For Elements One-step advantage, element For Elements The dominance of We get the second-step advantage ;when When , we can get the limit supermatrix; the limit supermatrix is ​​the weighted supermatrix Infinitely multiply by itself until the matrix becomes stable and no longer changes. At this time, the column vector of the matrix is ​​the global weight of the element; 2. Calculation of weights of each criterion in the risk assessment index system for tunnel construction in high-cold mountainous areas: According to the relevant steps in the above ANP overview, the weight calculation of each criterion in the risk assessment index system for tunnel construction in high-cold mountainous areas is carried out. The specific steps are as follows: (1) Determine the influence relationship between 17 sub-criteria in the risk assessment index system for tunnel construction in high-cold mountainous areas based on an expert questionnaire; (2) Use the 1-9 scaling method to construct a judgment matrix; (3) Construct a supermatrix and a weighted matrix, and then construct a weighted supermatrix based on them. Finally, the limit supermatrix is ​​obtained. At this time, the column vector of the matrix is ​​the global weight of the 17 sub-criteria in the risk assessment index system for tunnel construction in high-cold mountainous areas. Step 3: Construct a risk assessment model for tunnel construction in high-cold mountainous areas based on the ANP-matter-element normal cloud model: 1. Overview of the Matter-element Theory: Extenics is an original theory proposed by Chinese scholar Cai Wen. Its starting point is to use computer intelligence to deal with the contradictions existing in reality. In Extenics, matter-element Things ,feature and value The ordered triples formed; when a thing Multiple features at the same time (The corresponding value is ) characterizes, then The representation of the dimensional matter-element is shown in formula (6); where: for The sub-matter element of the dimension-matter element; (6) According to the relevant definitions of matter-element theory, the classical domain expression is shown in formula (7); (7) In formula (7), Indicates An evaluation thing, Indicates the first Features, Indicates the corresponding The range of values ​​is the classical domain; according to the relevant definition of matter-element theory, the section domain expression is shown in formula (8); (8) In formula (8), Indicates all rating levels. express About Features The value range of is the node domain; according to the relevant definition of matter-element theory, the expression of the matter-element to be evaluated is shown in formula (9); (9) In formula (9), represents the thing to be evaluated; according to the relevant definition of matter-element theory, the expression of the correlation function is shown in formula (10); (10) In formula (10), Indicates Among the items to be evaluated The evaluation index is about The correlation function of levels; where a point To interval The distance is shown in formula (11); (11) No. The object to be evaluated is about The comprehensive correlation of the levels The expression of is shown in formula (12); (12) In formula (12), Corresponding evaluation index The final evaluation level determined based on the maximum membership principle is shown in formula (13); (13) 2. Construction of matter-element-normal cloud model: The normal cloud model describes the uncertainty of the transformation between a qualitative concept and its numerical expression in words. It is assumed that the qualitative concept A is mapped to the domain U. Any element x in the domain U has a random number UA(x) with a stable tendency to the qualitative concept A, which is called the degree of certainty of x to the concept A. The evaluation attributes are described by the three digital features of expectation Ex, entropy En and super entropy He. These three digital features reflect the randomness and fuzziness of things, and make them interrelated, and express the relationship between qualitative concepts and quantitative indicators in the form of functions. The method of replacing the numerical eigenvalues ​​of the normal cloud model with the value of the characteristics of things in the traditional matter-element theory can effectively solve the problem of random fuzziness of things that cannot be solved in the matter-element theory. The improved matter-element matrix based on the normal cloud model, that is, the normal cloud-matter-element model expression is as follows: (14) The following are the main steps to establish a normal cloud-matter element model: (1) Convert interval values ​​into cloud parameters: The evaluation criteria are used as the interval number, and the upper and lower limits of the interval are used as To constrain the index, according to the 3En rule of normal cloud, the conversion formula of cloud parameters is expressed as: , , ; Where: , , They represent expectation, entropy, and super entropy respectively; It represents the minimum and maximum values ​​of the evaluation criteria interval; represents a constant of 0.05; (2) Calculate the correlation: The membership between the value of the indicator to be evaluated and each level is carried out according to the following steps: a. Computing Standard Cloud ; b. Get For expectations, Normal random number with standard deviation ; c. Find the relevance of cloud droplet x to the cloud of this level through the membership function: (15) d. Repeat the above steps N times, and take the average of the N results as the correlation degree; 3. Risk assessment method for tunnel construction in high-cold mountainous areas based on matter-element and normal cloud model: According to the above-mentioned matter-element theory overview and the relevant discussion in the construction of the matter-element-normal cloud model, a high-cold mountain tunnel construction risk assessment model based on the matter-element and normal cloud model is constructed. The specific steps are as follows: (1) Dimensionless processing of measured indicators: When conducting risk assessment of tunnel construction in high-cold mountainous areas, the units of various indicators have large differences, making it impossible to directly compare the evaluation indicators. It is necessary to first perform dimensionless processing on the evaluation indicators so that the dimensions of each indicator are between [0, 1], so that the indicators are directly comparable before evaluation; (2) Determine the standard cloud of the evaluation index: According to the 3En rule of the normal cloud and the conversion formula of the cloud parameters, determine the standard cloud of the risk assessment index system for tunnel construction in high-cold mountainous areas; (3) Calculate the correlation: Calculate the correlation of each evaluation index in the high-cold mountain tunnel construction risk assessment index system according to formula (15). Since the correlation of the cloud calculated by formula (15) is random, it is necessary to weaken its influence through multiple operations and take the median to obtain the correlation of each evaluation index. (4) Determine the evaluation level: Determine the risk assessment index system for tunnel construction in high-altitude and cold mountainous areas, and the level of the indicators to be evaluated j The formula for the comprehensive correlation is: (16) The formula for determining the overall result of the risk assessment of tunnel construction in high-cold mountainous areas is as follows: (17) Step 4: Dynamically analyze the potential risks in the construction process of tunnels in high-cold mountainous areas: 1. Real-time monitoring and data collection: Use modern information technology (such as the Internet of Things, big data, artificial intelligence, etc.) to conduct real-time monitoring and data collection of key parameters during tunnel construction, including geological deformation monitoring, meteorological data, construction equipment status, etc.; 2. Dynamic risk assessment: Input real-time monitoring data into the ANP-matter-element normal cloud evaluation model to conduct real-time or regular risk assessment; by comparing historical data with the current status, identify the trend of risk changes and promptly warn of potential risks; 3. Risk response and adjustment: Based on the assessment results, formulate corresponding risk response strategies and measures, such as adjusting the construction plan, strengthening safety protection, optimizing resource allocation, etc. At the same time, dynamically adjust the risk assessment model and parameters according to the construction progress and changes in the external environment to ensure the timeliness and effectiveness of the assessment.

[0032] In an exemplary embodiment, the tunnel construction risk assessment method based on ANP and matter-element normal cloud model is implemented in the following manner: (1) The weights of each indicator in the indicator system obtained using the ANP method are shown in Table 10; Table 10: Comprehensive weight matrix of each indicator

[0033] (2) The measured data of each indicator and the interval of the evaluation level are dimensionlessly processed. The results after processing are shown in Table 11; Table 11: Measured data of each indicator and corresponding evaluation level after dimensionless processing

[0034] (3) Determine the level standard cloud of the evaluation index according to the following cloud parameter conversion formula. The cloud parameters of the standard cloud are shown in Table 12; , Table 12: Measured data of each indicator and corresponding evaluation level after dimensionless processing

[0035] Among them, the data in brackets in Table 12 are , , ; (4) Calculate the correlation The membership between the value of the indicator to be evaluated and each level is carried out according to the following steps: a. Computing Standard Cloud ; b. Get a normal random number with En as the expectation and He as the standard deviation ; c. Find the relevance of cloud droplet x to the cloud of this level through the membership function: , d. Repeat the above steps N times, and take the average of the N results as the correlation degree; The correlation between the final calculated values ​​of the indicators to be evaluated and each level is shown in Table 13; Table 13: Correlation between estimated index values ​​and various levels

[0036] (5) Determine the evaluation level Determine the risk assessment index system for tunnel construction in high-cold mountainous areas, and the level of the indicators to be evaluated j The formula for the comprehensive correlation is:

[0037] The formula for determining the overall result of the risk assessment of tunnel construction in high-cold mountainous areas is as follows:

[0038] It can be seen that the technical solution of the present invention can realize quantitative assessment of risks, accurately describe the ambiguity and randomness of risks, and realize a comprehensive, dynamic and accurate assessment of tunnel construction risks in high-altitude and cold mountainous areas, and has strong practicality.

[0039] This embodiment provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the above-mentioned tunnel construction risk assessment method based on ANP and matter-element normal cloud model.

[0040] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation modes, which are merely illustrative rather than restrictive. Under the guidance of the present invention, ordinary technicians in this field can also make many forms without departing from the scope of protection of the present invention and the claims, all of which are within the protection of the present invention.

Claims

1. A tunnel construction risk assessment method based on ANP and matter-element normal cloud model, characterized in that: The following steps are involved: S1: according to the main risk factors affecting the construction of tunnels in high-cold mountainous areas, a risk assessment index system for the construction of tunnels in high-cold mountainous areas is obtained, wherein the risk assessment index system for the construction of tunnels in high-cold mountainous areas includes at least one criterion, and the criterion includes at least one sub-criterion; S2: Based on the risk assessment index system for tunnel construction in high-cold mountainous areas, the weight of each index is obtained using the network analysis method; S3: Based on the risk assessment index system for tunnel construction in high-altitude and cold mountainous areas and the weights of each index, the matter-element theory and the normal cloud model are used to conduct risk assessment on tunnel construction in high-altitude and cold mountainous areas, and the overall result of risk assessment on tunnel construction in high-altitude and cold mountainous areas is obtained.

2. The tunnel construction risk assessment method based on ANP and matter-element normal cloud model according to claim 1 is characterized in that: The risk assessment index system for tunnel construction in high-cold mountainous areas includes the following criteria: geological factors, groundwater factors, design and construction factors, organizational and management factors, and natural environment factors; the geological factors include the following sub-criteria: surrounding rock grade, fracture zone, unfavorable geology, bias angle, and burial depth ratio; the groundwater factors include the following sub-criteria: groundwater level and groundwater inflow; the design and construction factors include the following sub-criteria: stratum reinforcement method, excavation method, excavation span, support method, blasting disturbance, and monitoring measurement; The organizational and management factors include at least the following sub-criteria: construction management; The natural environmental factors include at least the following sub-criteria: annual average temperature, air oxygen content, and annual average rainfall.

3. The tunnel construction risk assessment method based on ANP and matter-element normal cloud model according to claim 1 is characterized in that: Step S2 specifically includes: S21: Based on the risk assessment index system for tunnel construction in high-cold mountainous areas, the influence relationship between the sub-criteria is obtained by using the expert questionnaire method; S22: according to the influence relationship between the sub-criteria, a judgment matrix is ​​obtained by using a 1-9 scaling method; S23: According to the judgment matrix, the global weights of all sub-criteria are calculated using the network analysis method to obtain the weights of each indicator.

4. The tunnel construction risk assessment method based on ANP and matter-element normal cloud model according to claim 3 is characterized in that: Step S23 specifically includes: S231: Obtain a supermatrix according to the judgment matrix; S232: constructing a new judgment matrix by taking each element group as a sub-criteria and comparing the importance of the element groups in pairs to obtain a weighted matrix, and obtaining a weighted super-matrix according to the weighted matrix and the super-matrix; S233: infinitely multiplying the weighted supermatrix by itself until the matrix becomes stable and no longer changes, thereby obtaining the weights of each indicator.

5. The tunnel construction risk assessment method based on ANP and matter-element normal cloud model according to claim 1 is characterized in that: Step S3 specifically includes: S31: Dimensionless processing is performed on the measured values ​​of the risk assessment index system for tunnel construction in high-cold mountainous areas to obtain dimensionless values ​​of the evaluation indexes; S32: Determine a standard cloud of the evaluation index according to the dimensionless value of the evaluation index by using matter-element theory and a normal cloud model; S33: Obtaining the correlation degree of each evaluation indicator according to the standard cloud of the evaluation indicators; S34: According to the correlation between the evaluation indicators, the overall result of the risk assessment of tunnel construction in the high-cold mountainous area is obtained.

6. The tunnel construction risk assessment method based on ANP and matter-element normal cloud model according to claim 5 is characterized in that: Step S32 specifically includes: according to the dimensionless value of the evaluation index, using matter-element theory and normal cloud model, determining the standard cloud of the evaluation index, such as formula: ， ， ， in, , , They represent the expectation, entropy, and super entropy of the standard cloud of the evaluation index respectively; , It represents the minimum and maximum values ​​of the dimensionless value of the evaluation index and the evaluation standard interval; Is a constant.

7. The tunnel construction risk assessment method based on ANP and matter-element normal cloud model according to claim 5 is characterized in that: Step S33 specifically includes: obtaining the correlation degree of each evaluation indicator according to the standard cloud of the evaluation indicator, such as the formula: ， in, is the correlation degree of each evaluation index, Cloud droplets representing the normal cloud model, For For expectations, is a normal random number with standard deviation .

8. The tunnel construction risk assessment method based on ANP and matter-element normal cloud model according to claim 5 is characterized in that: Step S34 specifically includes: obtaining the overall result of the risk assessment of tunnel construction in high-cold mountainous areas according to the correlation of the evaluation indicators, such as the formula: ， ， in, For the indicators to be evaluated about the level The comprehensive correlation of For the The comprehensive weight of the indicators, K j ( v i ) is the Indicators about The correlation of the rating levels, This is the overall result of the risk assessment for tunnel construction in high-altitude mountainous areas.

9. The tunnel construction risk assessment method based on ANP and matter-element normal cloud model according to claim 1 is characterized in that: The tunnel construction risk assessment method based on ANP and matter-element normal cloud model also includes: dynamic analysis of potential risks in the tunnel construction process in high-altitude mountainous areas, specifically including: real-time monitoring and data collection of key parameters in the tunnel construction process, using steps S1-S3 to conduct risk assessment, and by comparing historical data with the current status, identify the trend of risk changes and timely warn of potential risks; formulate corresponding risk response strategies and measures based on the assessment results; and adjust the risk assessment model and parameters according to the construction progress and changes in the external environment.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the tunnel construction risk assessment method based on ANP and matter-element normal cloud model described in any one of claims 1 to 9 are implemented.

Images