Operation tunnel safety evaluation method and system based on variable weight and finite cloud model

Abstract

The invention discloses a variable weight and finite cloud model-based operation tunnel safety evaluation method and system. The method comprises the following steps of: constructing a safety evaluation index system of an operation period shield tunnel structure; based on the safety evaluation index system, an improved CRITIC method is adopted to solve the constant weight of each evaluation index; according to a variable weight theory, establishing a penalty state vector considering shield tunnel disease characteristics, and calculating a dynamic variable weight of an evaluation index; calculating a single index membership degree of each security level by adopting a finite interval cloud model method; and performing comprehensive calculation on the dynamic variable weight and the single index membership degree to obtain a comprehensive membership degree of each safety level, and determining the safety level of the operating shield tunnel structure according to a maximum membership degree principle. According to the method, qualitative and quantitative conversion of the shield tunnel safety evaluation indexes can be realized, and the problems of randomness and fuzziness in the evaluation process are solved.

Description

Technical Field

[0001] The present invention belongs to the technical field of shield tunnel structure safety assessment, and particularly relates to an operation tunnel safety evaluation method and system based on variable weight and finite cloud model. Background Art

[0002] At present, certain progress has been made in the shield tunnel structure safety evaluation technology. For example, the detection method based on machine vision and deep learning technology can achieve the automatic identification and quantitative analysis of tunnel diseases. By using mobile laser scanning technology to obtain three-dimensional point cloud data and combining deep learning algorithms, diseases such as cracks, water leakage, and spalling of tunnel linings can be efficiently detected. In addition, some research has proposed a comprehensive evaluation method based on semi-supervised learning and stacking algorithms. By improving the multi-dimensional normal cloud model and optimizing the performance of the classifier, the accuracy and reliability of tunnel safety evaluation have been further improved.

[0003] However, there are still some deficiencies in the existing technology. On the one hand, the traditional constant weight evaluation method does not fully consider the mutual influence between tunnel diseases, resulting in unbalanced and unreasonable evaluation results. On the other hand, although the traditional cloud model for shield tunnel structure safety evaluation can handle randomness and fuzziness, it requires the index grade interval to follow an infinite interval normal distribution, which does not conform to the complex characteristics of actual operation shield tunnel diseases, thus affecting the accuracy of the evaluation results. Summary of the Invention

[0004] To solve the above technical problems, the present invention proposes an operation tunnel safety evaluation method and system based on variable weight and finite cloud model to solve the problems existing in the above-mentioned prior art.

[0005] To achieve the above object, in the first aspect, the present invention provides an operation tunnel safety evaluation method based on variable weight and finite cloud model, including:

[0006] Construct a safety evaluation index system for the shield tunnel structure during the operation period;

[0007] Based on the safety evaluation index system, use the improved CRITIC method to solve the constant weights of each evaluation index; according to the variable weight theory, establish a penalty type state vector considering the characteristics of shield tunnel diseases, and calculate the dynamic variable weights of the evaluation indexes;

[0008] Use the finite interval cloud model method to calculate the single-index membership degrees of each safety level;

[0009] Comprehensively calculate the dynamic variable weights and the single-index membership degrees to obtain the comprehensive membership degrees of each safety level, and determine the safety level of the shield tunnel structure during operation according to the maximum membership degree principle.

[0010] Preferably, the process of constructing a safety evaluation index system for shield tunnel structures during the operation period includes:

[0011] Identifying disease factors that affect the safety of shield tunnel structures during the operation period, and determining evaluation indexes based on the disease factors;

[0012] Classifying the safety of shield tunnel structures during operation to obtain a classification result;

[0013] Based on the classification result, dividing the safety level thresholds of each safety evaluation index to obtain a threshold division result;

[0014] Based on the evaluation indexes, classification results, and threshold division results, constructing a safety evaluation index system.

[0015] Preferably, the disease factors include: material deterioration, segment spalling, segment deformation, lining cracks, leakage, and cavities;

[0016] Each disease factor contains several evaluation indexes;

[0017] Among them, the material deterioration includes: the reduction ratio of lining strength, the deterioration state of the lining, and steel bar corrosion;

[0018] The segment spalling includes: the spalling range, spalling diameter, and spalling depth;

[0019] The segment deformation includes: convergence of the clearance, circumferential offset, and radial offset;

[0020] The lining cracks include: crack length, crack width, and crack depth ratio;

[0021] The leakage includes: leakage water volume, leakage state, and pH value;

[0022] The cavities include: longitudinal length and area.

[0023] Preferably, the process of solving the constant weights of each evaluation index includes:

[0024] Based on the evaluation index values of the safety evaluation index system, constructing an original evaluation matrix to obtain an initial shield tunnel disease data set;

[0025] According to the selected tunnel index type, normalizing the initial shield tunnel disease data set to obtain a normalized matrix;

[0026] Based on the normalized matrix, calculating the coefficient of variation of the evaluation index;

[0027] Based on the normalized matrix, calculating the correlation coefficient between each evaluation index;

[0028] Calculate the comprehensive coefficient of each evaluation index based on the coefficient of variation and the correlation coefficient;

[0029] Calculate the constant weight of each evaluation index based on the comprehensive coefficient.

[0030] Preferably, the process of calculating the dynamic variable weight of the evaluation index includes:

[0031] Based on the normalization matrix, select an exponential function to construct a state variable weight vector;

[0032] Calculate the dynamic variable weight of the evaluation index based on the state variable weight vector and the constant weight.

[0033] Preferably, the process of calculating the single-index membership degree of each safety level includes:

[0034] Based on the value range of different levels of each evaluation index in the safety evaluation index system, use the finite interval cloud model method to calculate the digital characteristics of each evaluation index;

[0035] Based on the digital characteristics and the preset number of cloud droplets, use the forward finite interval cloud generator to generate the finite interval cloud distribution diagram of each evaluation index;

[0036] Based on the finite interval cloud distribution diagram, obtain the single-index membership degree of each safety level.

[0037] Preferably, the calculation formula of the comprehensive membership degree is;

[0038]

[0039] In the formula, μ kj represents the membership degree of the index j to the level k in the sample measurement value or evaluation value, and W(j) is the dynamic variable weight.

[0040] In the second aspect, the present invention also discloses an operation tunnel safety evaluation system based on variable weight and finite cloud model, including:

[0041] A system construction module for constructing a safety evaluation index system for the shield tunnel structure during the operation period;

[0042] A first calculation module for solving the constant weight of each evaluation index based on the safety evaluation index system by using the improved CRITIC method; establishing a penalty-type state vector considering the disease characteristics of the shield tunnel according to the variable weight theory, and calculating the dynamic variable weight of the evaluation index;

[0043] A second calculation module for calculating the single-index membership degree of each safety level by using the finite interval cloud model method;

[0044] The level evaluation module is used to comprehensively calculate the dynamic variable weights and the single-index membership degrees to obtain the comprehensive membership degrees of each safety level, and determine the safety level of the operating shield tunnel structure according to the principle of maximum membership degree.

[0045] Thirdly, the present invention also discloses a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method described in the first aspect are implemented.

[0046] Fourthly, the present invention also discloses a computer program product, including a computer program. When the computer program is executed by a processor, the steps of the method described in the first aspect are implemented.

[0047] Compared with the prior art, the present invention has the following advantages and technical effects:

[0048] The present invention provides a safety evaluation method for operating tunnels based on variable weights and the finite cloud model. Firstly, a safety evaluation index system for shield tunnel structures during the operation period is constructed; secondly, based on the safety evaluation index system, an improved CRITIC method is used to solve the constant weights of each evaluation index; according to the variable weight theory, a penalty-type state vector considering the disease characteristics of shield tunnels is established to calculate the dynamic variable weights of the evaluation indexes; then, the finite interval cloud model method is used to calculate the single-index membership degrees of each safety level; finally, the dynamic variable weights and the single-index membership degrees are comprehensively calculated to obtain the comprehensive membership degrees of each safety level, and the safety level of the operating shield tunnel structure is determined according to the principle of maximum membership degree.

[0049] The present invention uses the improved CRITIC method to calculate the constant weights. By introducing the coefficient of variation and the positive and negative correlation coefficients, the calculation accuracy of the constant weights of the evaluation indexes is significantly improved. At the same time, the dynamic variable weights are calculated in combination with the variable weight theory, effectively solving the problem that the state of the tunnel structure changes dynamically due to the interaction between diseases, thereby improving the rationality of the evaluation results;

[0050] The present invention introduces the finite interval cloud model, fully considering the characteristic that when the index value exceeds the range of the mean values of the cloud at both ends of the grade, the cloud droplet distribution changes from a normal distribution to a uniform distribution with a membership degree of 1. This improvement accurately reflects the distribution characteristics of the evaluation indexes within a finite interval, overcomes the limitation that the traditional cloud model requires the index grade interval to be an infinite interval normal distribution, and makes the safety evaluation results of tunnel diseases closer to the actual situation. Description of the Drawings

[0051] The drawings constituting a part of this application are used to provide a further understanding of this application. The schematic embodiments of this application and their descriptions are used to explain this application and do not constitute an improper limitation to this application. In the drawings:

[0052] Figure 1Flow chart of the evaluation method according to the embodiments of the present invention;

[0053] Figure 2 Cloud droplet diagram of the operation shield tunnel safety evaluation index according to the embodiments of the present invention;

[0054] Figure 3 Status quo diagram of the shield tunnel section of the engineering application case according to the embodiments of the present invention. Detailed implementation manners

[0055] It should be noted that, without conflict, the embodiments in the present application and the features in the embodiments may be combined with each other. The present application will be described in detail below with reference to the drawings and in combination with the embodiments.

[0056] It should be noted that the steps shown in the flowchart of the drawings can be executed in a computer system such as a set of computer-executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than here.

[0057] Embodiment 1

[0058] As Figure 1 shown, in this embodiment, a safety evaluation method for operating tunnels based on variable weights and the finite cloud model is provided, including:

[0059] S1. Construct a safety evaluation index system for the structure of the shield tunnel during the operation period;

[0060] In step S1 of this embodiment, the process of constructing the safety evaluation index system for the structure of the shield tunnel during the operation period includes:

[0061] S101. First, identify the disease factors that have a significant impact on the safety of the shield tunnel structure during the operation period, select relevant parameters based on the disease factors, and then determine the corresponding safety evaluation indexes;

[0062] Through the analysis of the factors affecting the safety of the shield tunnel structure during the operation period, six disease factors are determined: material deterioration, segment spalling, segment deformation, lining cracks, water leakage, and cavities or non-compaction, and corresponding safety evaluation indexes are set for each factor;

[0063] Material deterioration includes three indexes: the reduction ratio of the lining strength, the deterioration state of the lining, and the corrosion of the steel bars;

[0064] Segment spalling covers three indexes: the spalling range, the spalling diameter, and the spalling depth;

[0065] Segment deformation involves three indexes: the convergence of the clearance, the circumferential dislocation, and the radial dislocation;

[0066] Lining cracks include three indexes: the crack length, the crack width, and the crack depth ratio;

[0067] The seepage water includes three indicators: seepage water volume, seepage water state, and pH value;

[0068] Holes or non-compaction include two indicators: longitudinal length and area.

[0069] S102. Classify the structural safety level of the operating shield tunnel;

[0070] According to the "Technical Specification for Operation Monitoring of Urban Rail Transit Facilities - Part 3: Tunnels" and the "Technical Specification for Tunnel Structure Maintenance of Urban Rail Transit", the structural safety level of the shield tunnel is divided into 5 levels, and the corresponding safety states are levels I, II, III, IV, and V. The safety evaluation level division of shield tunnel diseases is as shown.

[0071] Table

[0072]

[0073] S103. According to the classification results of step S102, divide the safety level thresholds of each safety evaluation index, and the division results are as shown.

[0074] Table

[0075]

[0076] S104. Based on the results of steps S101, S102, and S103, obtain the safety evaluation index system of the operating shield tunnel containing two layers of safety evaluation indexes.

[0077] S2. Based on the safety evaluation index system, use the improved CRITIC method to solve the constant weight w(x) of each index; according to the variable weight theory, establish a penalty-type state vector calculation index dynamic variable weight W(X) considering the characteristics of shield tunnel diseases;

[0078] Furthermore, in step S2, according to the established shield tunnel structural safety evaluation index system, use the improved CRITIC method to determine the constant weight of the evaluation index, introduce the coefficient of variation method to represent the comparison intensity of the index, solve the influence of the order of magnitude and dimension differences between safety evaluation indexes on the weight, and reflect the conflict degree between indexes through the absolute value of the correlation coefficient, fully considering the positive and negative correlations between indexes. The process of calculating the constant weight includes:

[0079] S201. According to the evaluation index values of the evaluation tunnel section, construct the original evaluation matrix to obtain the initial shield tunnel disease data set ;

[0080] Where m is the number of samples for the safety assessment of shield tunnels, n is the number of safety assessment indicators for shield tunnels, and t ij is the value of the j-th assessment indicator for the i-th assessment tunnel section;

[0081] S202. The safety assessment indicators for tunnel structures are divided into two types: benefit type and cost type. According to the selected tunnel indicator type, the initial shield tunnel disease dataset is normalized to eliminate the influence of different dimensions on the assessment results, and a normalized matrix is obtained ;

[0082] Benefit type indicators:

[0083]

[0084] Cost type indicators:

[0085]

[0086] S203. To address the defect that directly using the standard deviation to reflect the comparison intensity of indicators, the coefficient of variation method is adopted to calculate the standard deviation rate for improvement, and the coefficient of variation v of the assessment indicators is calculated j , ;

[0087] In the formula, v j is the coefficient of variation of the j-th tunnel structure safety assessment indicator, is the mean value of the j-th tunnel structure safety assessment indicator, is the mean square deviation of the j-th tunnel structure safety assessment indicator;

[0088] S204. Calculate the correlation coefficient between each assessment indicator ;

[0089]

[0090] In the formula, , x ik and x il are the standardized values of the scoring scores of the k-th and l-th assessment indicators for the i-th assessment tunnel section respectively;

[0091] S205. The absolute value of the correlation coefficient is used to represent the conflict situation of indicators, making up for the deficiency of only using the positive correlation coefficient to reflect the degree of indicator conflict, and calculating the comprehensive coefficient c of each assessment indicator j , ;

[0092] S206. Calculate the constant weight w of each assessment indicator j , .

[0093] As an innovative implementation method, in step S2, the constant weights of the tunnel safety evaluation indicators are dynamically corrected based on the variable weight theory. In the index weighting method, the constant weight theory is usually adopted. Even when using the comprehensive weighting method to combine subjective and objective weights, the resulting result is still the comprehensive constant weight, that is, the weights of each index do not change with the change of the evaluation samples. However, due to the interaction between tunnel structure diseases, the tunnel state changes dynamically, and in some tunnel sections, specific diseases may not exist or are limited by on-site investigation conditions, not all indicators are applicable to evaluate the safety state of the tunnel structure. Therefore, it is necessary to dynamically adjust the initial weights according to the actual situation of the disease development. The calculation process of the dynamic variable weight includes:

[0094] S207. Adopt the normalized matrix calculated in step S202 ;

[0095] S208. Select the exponential function to construct the state variable weight vector ;

[0096]

[0097] In the formula, a is the sensitivity of the index, reflecting the sensitivity of the evaluation tunnel section to a certain disease factor; β is the penalty level. When the value x of the state of the j-th tunnel safety evaluation index is lower than the penalty level β, S j (x i ) increases rapidly with its decrease, and then increases its final weight, achieving the effect of reducing the overall score of the tunnel.

[0098] S209. Combine the constant weights obtained in step S206 to calculate the dynamic variable weights of the indicators ;

[0099]

[0100] Calculating the dynamic optimal weights of the tunnel safety evaluation indicators using the variable weight theory not only avoids the phenomenon of weight imbalance, but also fully considers the influence of the self-state values of the tunnel disease factor evaluation indicators on the weights. To a certain extent, it dynamically corrects the constant weights, overcomes the errors in the safety evaluation process caused by fixed weights, and provides reasonable support for the safety evaluation of operating shield tunnels.

[0101] S3. Adopt the finite interval cloud model method to calculate the single-index membership degree μ of each safety level kj ;

[0102] As an innovative implementation method, in step S3, the process of calculating the single-index membership degree includes:

[0103] S301. According to the value ranges of different grade intervals of each evaluation index in the shield tunnel structure safety evaluation index system, calculate the digital characteristics of each index;

[0104] The index grading standard is divided into a bilateral constraint index interval: and a unilateral constraint index interval: or , and the digital feature calculation formula for the bilateral constraint index interval is:

[0105]

[0106] In the formula, 、 and are the expectation, entropy, and hyper-entropy of the tunnel safety evaluation level interval k, respectively; and represent the upper critical value and the lower critical value of the index interval k, respectively, represents the order of the normal density function within the finite interval, taking the largest integer. is an empirical value, taking 0.01.

[0107] The calculation formula of

[0108]

[0109] is as follows: is or .

[0110] The unilateral constraint index interval can adopt symmetry, and the upper limit value or the lower limit value calculation formula of the interval is calculated by using the midpoint value of the adjacent interval and its half interval length:

[0111]

[0112] Then, the digital features of this interval are obtained by using the above formula, so as to realize the conversion between the qualitative analysis and the quantitative analysis of the tunnel safety evaluation index. The digital features of the safety evaluation indexes of each grade calculated such as shown.

[0113] Table

[0114]

[0115] S302. Digital Features Based on the Finite Interval Cloud Model and the preset number of cloud droplets , use the forward finite interval cloud generator to generate a distribution map containing cloud droplets; when the evaluation index value is within the mean value range of the two end grade clouds, the cloud droplets It is normally distributed within a finite interval; when the index value deviates from the expected values of the two ends of the cloud, it is uniformly distributed with a membership degree of 1; therefore, It follows a uniform distribution and a normal distribution in a finite interval, and its formula is:

[0116]

[0117] In the formula: represents the expected value of the leftmost interval; represents the expected value of the rightmost interval; represents the random number generated according to E x and He; represents the maximum value of the rightmost interval, where .

[0118] Based on the aforementioned finite interval cloud model and the evaluation index grading standard, 1000 cloud droplets are generated by a forward finite cloud generator to form a finite interval cloud distribution diagram of each evaluation index (as Figure 2 shown). By analyzing the cloud diagram, the membership degree of index j to level k can be obtained. In the figure, the horizontal axis represents the value of the tunnel safety evaluation index, and the vertical axis represents the membership degree of the cloud droplets at a specific safety level.

[0119] The finite interval normal distribution considers that when the evaluation index of tunnel disease factors is outside the mean values of the two ends of the grade cloud, the cloud droplets no longer belong to the normal distribution, but are uniformly distributed with a membership degree of 1, which can reflect the characteristics of the finite interval distribution of the evaluation index, avoiding the shortcomings of the traditional cloud model where the index grade interval is an infinite interval normal distribution, making the tunnel disease safety evaluation result more in line with the actual situation.

[0120] In this embodiment, in the structural safety evaluation of shield tunnels, the finite interval cloud model is innovatively applied to overcome the shortcoming of the traditional cloud model that requires the tunnel evaluation index interval to be an infinite interval normal distribution.

[0121] S4. The dynamic variable weight vector W(X) and the single-index membership degree μ kj are comprehensively calculated to obtain the comprehensive membership degree of each safety level, and the structural safety level L of the operating shield tunnel is determined according to the maximum membership degree principle.

[0122] Furthermore, in step S4, the calculation process of obtaining the structural safety level of the operating shield tunnel includes:

[0123] S401. Calculate the comprehensive membership degree μ k of each evaluation level. The comprehensive membership degree is the sum of the products of the membership degrees of each level of each evaluation index and the corresponding dynamic variable weight vector. The calculation formula is:

[0124]

[0125] In the formula, represents the membership degree of index j to level k in the sample measurement value or evaluation value;

[0126] S402. According to the principle of maximum membership degree, the final membership degree is the level corresponding to the maximum value in the calculated comprehensive membership degree set:

[0127] .

[0128] This embodiment illustrates the above method with an actual processing example:

[0129] 1. General situation of the research area:

[0130] To better determine the accuracy of the safety evaluation model, four tunnel sections, namely the left and right lines of the Anhuaqiao - Andeli Beijie and Andeli Beijie - Gulou Dajie sections of the operation tunnel of Beijing Subway Line 8, are selected for safety evaluation.

[0131] The tunnel structure forms of the An'an section and the Angu section of Subway Line 8 are both shield tunnels. It is found through investigation that the water flow in the pump house at the connection passage of the An'an section and the Angu section is relatively large, resulting in water accumulation within a certain range of the central drainage ditch of the adjacent tunnel. The current situation of the section is as Figure 3 shown.

[0132] To ensure the safety of the subway structure, structural status surveys and detections are carried out on the two sections. The detection contents include structural appearance surveys, structural crack detections, hollow drum detections, tunnel ovality, concrete strength, protective layer thickness, peeling between the roadbed and the structural floor slab, tunnel clearance convergence, and overall deformation of the connection passage, etc. According to the detection results, the disease conditions of the tunnels in the evaluation section are summarized according to the proposed indicators, as shown in shown.

[0133] Table

[0134]

[0135] 2. Calculation results of index weights:

[0136] Calculate the constant weights. According to the disease conditions of the four sample evaluation sections summarized, four typical samples are established to form the original safety evaluation matrix of shield tunnel diseases :

[0137]

[0138] Normalize the original evaluation matrix where , , , , are benefit - type indicators, , , , , , , , , , , , are cost - type indicators. By calculating, the normalized evaluation index matrix of four sample intervals is obtained , and the coefficient of variation and correlation coefficient of each safety evaluation index are calculated to obtain the constant weight of each index , as shown in .

[0139]

[0140] Calculate the variable weight, and the state variable weight vector S j (x i ) takes a = 0.5 and β = 0.7, so as to calculate the dynamic variable weights W(X) of the four sample indicators. The calculation results are shown in .

[0141] Table

[0142]

[0143] 3. Calculation results of single - index membership degree:

[0144] According to the shield tunnel disease safety evaluation index data of the four samples obtained, combined with the finite - interval cloud model equation and the forward finite cloud generator, calculate the membership degree of each index at different safety levels. The calculation results of sample 1 are as shown in .

[0145] Table

[0146]

[0147] 4. Calculation results of comprehensive membership degree:

[0148] Determine the comprehensive membership degree of the sample based on each safety level according to the index dynamic variable weight. According to the maximum membership degree principle, determine the final safety evaluation level of the sample. The comprehensive membership degree and evaluation level of the sample are as follows:

[0149] ;

[0151] ;

[0153] ;

[0155] ;

[0157] In summary, the safety evaluation grades of the four samples can be obtained. The safety evaluation grade of Sample 1 is Grade II, the safety rating of Sample 2 is Grade IV, and Samples 4 and 5 are Grade I, indicating that the tunnel is safer. According to the "Technical Specification for Maintenance of Urban Rail Transit Facilities" (DB 11 / T 718 - 2016), the evaluation results are summarized in , and the overall safety status evaluations of Samples 1 and 2 in the detection range are both Grade II, while the overall safety status evaluations of Samples 3 and 4 are both Grade I. Using the model in this paper to evaluate Sample 1, 3, and 4 gives the same results as the specification evaluation. However, the safety evaluation index data of Sample 2 has a greater impact on the safety of the operating shield tunnel, indicating that the operating shield tunnel is more dangerous. Therefore, the evaluation result of the model in this paper is Grade IV. From the sample evaluation results, it can be seen that the weights of the safety evaluation indexes for different samples are different, and the evaluation values of each index for the tunnel samples with a higher grade are higher than those of the tunnel samples with a lower grade. This objectively reflects the change in the impact of safety evaluation indexes on the safety of the operating shield tunnel, enabling the dynamic analysis of the safety evaluation of the shield tunnel, which is more in line with the actual situation of the operating shield tunnel. The evaluation results demonstrate the reliability of the model.

[0158] Advantages of this embodiment:

[0159] (1) For the structural safety evaluation of the operating shield tunnel, this embodiment classifies the safety evaluation indexes into five levels according to relevant standards and specifications, and constructs an evaluation system including 6 first-level indexes and 17 second-level indexes. This system provides a scientific reference for the structural safety evaluation of the operating shield tunnel.

[0160] (2) The improved CRITIC method is used to calculate the constant weights, which comprehensively considers the conflict, fluctuation degree among safety evaluation indexes, and the differences in disease characteristics of different tunnel sections. At the same time, the variable weight theory is introduced to dynamically adjust the constant weights, enabling the index weights to be adjusted according to the changes in the evaluation index values, which is closer to the actual requirements.

[0161] (3) The finite interval cloud model is introduced into the health evaluation of the shield tunnel lining. This model not only solves the problems of fuzziness and randomness in the evaluation process but also better reflects the interval distribution characteristics of the tunnel evaluation indexes by converting the infinite interval normal distribution of the traditional cloud model into a finite interval normal distribution.

[0162] (4) Apply the constructed safety evaluation model to the safety evaluation of a total of four sections of tunnels, namely the left and right lines of the sections from Anhuaqiao to Andeli Beijie and from Andeli Beijie to Gulou Dajie on Beijing Subway Line 8. The results show that sample 1 is rated as level II, sample 2 is rated as level IV, and samples 3 and 4 are rated as level I, which is relatively consistent with the specification evaluation results (samples 1 and 2 are level II, and samples 3 and 4 are level I), indicating that the model is more reasonable and accurate. The present invention verifies the accuracy of the model through actual application cases, provides reliable technical support for the safety evaluation of the operating shield tunnel state, and at the same time creates new evaluation ideas and methods.

[0163] Embodiment 2

[0164] Based on the same inventive concept, this embodiment also provides an operating tunnel safety evaluation system based on variable weights and a finite cloud model, including:

[0165] A system construction module for constructing a safety evaluation index system for the structure of a shield tunnel during the operation period;

[0166] A first calculation module for solving the constant weights of each evaluation index by using the improved CRITIC method based on the safety evaluation index system; according to the variable weight theory, establishing a penalty-type state vector considering the disease characteristics of the shield tunnel, and calculating the dynamic variable weights of the evaluation indexes;

[0167] A second calculation module for calculating the single-index membership degrees of each safety level by using the finite interval cloud model method;

[0168] A level evaluation module for comprehensively calculating the dynamic variable weights and the single-index membership degrees to obtain the comprehensive membership degrees of each safety level, and determining the safety level of the operating shield tunnel structure according to the maximum membership degree principle.

[0169] The operating tunnel safety evaluation system based on variable weights and a finite cloud model provided in this embodiment has all the advantages of the operating tunnel safety evaluation method based on variable weights and a finite cloud model provided in Embodiment 1.

[0170] Embodiment 3

[0171] This embodiment also discloses a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the method described in Embodiment 1 are implemented.

[0172] Embodiment 4

[0173] This embodiment also discloses a computer program product, including a computer program, and when the computer program is executed by a processor, the steps of the method described in Embodiment 1 are implemented.

[0174] The above are only the preferred specific embodiments of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present application should be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A safety evaluation method for operating tunnels based on variable weight and finite cloud model, characterized in that: The following steps are involved: Construct a safety evaluation index system for shield tunnel structures during operation; Based on the safety evaluation index system, the improved CRITIC method is used to solve the constant weight of each evaluation index; Based on the variable weight theory, a penalty state vector considering the characteristics of shield tunnel defects is established, and the dynamic variable weight of the evaluation index is calculated. The finite interval cloud model method is used to calculate the single index membership of each security level; The dynamic variable weight and the single indicator membership are comprehensively calculated to obtain the comprehensive membership of each safety level, and the safety level of the operating shield tunnel structure is determined according to the maximum membership principle.

2. The method according to claim 1, characterized in that: The process of constructing a safety evaluation index system for shield tunnel structures during operation includes: Identify the damage factors that affect the structural safety of shield tunnels during operation, and determine evaluation indicators based on the damage factors; The structural safety of operating shield tunnels is graded and the grade classification results are obtained; Based on the division results, each safety evaluation indicator is divided into a safety level threshold value to obtain a threshold division result; Based on the evaluation indicators, grade division results, and threshold division results, a safety evaluation indicator system is constructed.

3. The method according to claim 2, characterized in that The disease factors include: material degradation, segment peeling, segment deformation, lining cracks, water leakage and voids; Each disease factor contains several evaluation indicators; The material degradation includes: lining strength reduction ratio, lining degradation state, and steel bar corrosion; The segment peeling includes: peeling range, peeling diameter, and peeling depth; The segment deformation includes: clearance convergence, circumferential misalignment, and radial misalignment; The lining cracks include: crack length, crack width, and crack depth ratio; The leakage water includes: leakage water amount, leakage water state, and pH value; The cavity includes: longitudinal length and area.

4. The method according to claim 1, characterized in that The process of solving the constant weights of each evaluation index includes: Based on the evaluation index values ​​of the safety evaluation index system, the original evaluation matrix is ​​constructed to obtain the initial shield tunnel disease data set; According to the selected tunnel indicator type, the initial shield tunnel disease data set is normalized to obtain a normalized matrix; Based on the normalized matrix, calculating the coefficient of variation of the evaluation index; Based on the normalized matrix, calculating the correlation coefficient between the evaluation indicators; Based on the coefficient of variation and the correlation coefficient, calculating the comprehensive coefficient of each evaluation index; Based on the comprehensive coefficient, the constant weight of each evaluation index is calculated.

5. The method according to claim 4, characterized in that The process of calculating the dynamic variable weight of the evaluation index includes: Based on the normalized matrix, an exponential function is selected to construct a state variable weight vector; Based on the state variable weight vector and the constant weight, the dynamic variable weight of the evaluation index is calculated.

6. The method according to claim 1, characterized in that The process of calculating the single index membership of each security level includes: Based on the value range of different level intervals of each evaluation indicator in the safety evaluation indicator system, a finite interval cloud model method is used to calculate the digital characteristics of each evaluation indicator; Based on the digital features and the preset number of cloud droplets, a finite interval cloud distribution map of each evaluation index is generated using a forward finite interval cloud generator; Based on the finite interval cloud distribution diagram, the single indicator membership of each security level is obtained.

7. The method according to claim 1, characterized in that The calculation formula of the comprehensive membership is: In the formula, μ kj It represents the membership of indicator j to level k in sample measurement or evaluation value, and W(j) is the dynamic variable weight.

8. An operational tunnel safety evaluation system based on variable weight and finite cloud model, characterized in that: include: System construction module, used to construct a safety evaluation index system for shield tunnel structures during operation; The first calculation module is used to solve the constant weight of each evaluation index based on the safety evaluation index system by using the improved CRITIC method; Based on the variable weight theory, a penalty state vector considering the characteristics of shield tunnel defects is established, and the dynamic variable weight of the evaluation index is calculated. The second calculation module is used to calculate the single index membership of each security level using a finite interval cloud model method; The grade evaluation module is used to comprehensively calculate the dynamic variable weight and the single indicator membership to obtain the comprehensive membership of each safety level, and determine the safety level of the operating shield tunnel structure according to the maximum membership principle.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

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 method according to any one of claims 1 to 7 are implemented.

Images