Mountainous area tunnel structure safety evaluation method, device and equipment and readable storage medium

Abstract

The invention provides a mountain area tunnel structure safety evaluation method, device and equipment and a readable storage medium, and relates to the technical field of tunnel structure safety evaluation analysis, and the method comprises the steps: obtaining a safety evaluation index of a tunnel structure; randomly generating a plurality of samples in a preset security level according to the security evaluation index to obtain a constructed sample set; combining the most unfavorable reference values of the safety evaluation indexes under the safety level to obtain a limit sample set; calculating the combined weight of each safety evaluation index based on a group decision, an AHP algorithm, an entropy weight method, a CRITIC method and a game theory; based on a TOPSIS decision-making method and the combined weight, determining a quantization interval where each second proximity value is located, and obtaining a training sample set; and training a preset extreme learning machine according to the training sample set to obtain a safety evaluation model, and inputting sample data of the to-be-evaluated tunnel structure into the safety evaluation model for evaluation to obtain a safety evaluation result. According to the invention, the accuracy of evaluation index weight calculation is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of tunnel structure safety evaluation and analysis, and in particular to a method, device, equipment and readable storage medium for evaluating the safety of a tunnel structure in a mountainous area. Background Art

[0002] The currently widely used tunnel structure safety evaluation method is the safety factor method in the existing tunnel design specifications, which evaluates the safety of the tunnel structure by calculating the safety factor of the structure. However, the existing safety factor method is calculated through the axial force index and bending moment index of the section. The safety factor of the tunnel structure section only considers the force influence of the secondary lining, and does not consider the influence of other factors on the safety of the tunnel structure, such as the geological conditions of the tunnel engineering, the characteristics of the lining structure and other influencing factors. Therefore, the evaluation result is not comprehensive enough. The common fuzzy comprehensive evaluation method only considers the subjective weight of the index. The determination of its weight value is affected by the subjective thinking of the expert, and is easily affected by the professional experience and professional knowledge level of the evaluator himself. It has high requirements on the level of the evaluator and lacks a certain degree of objectivity. In addition, the selection of the membership function in the fuzzy comprehensive evaluation method will have a certain impact on the accuracy of the evaluation results, and the maximum membership principle is not applicable in some cases. Summary of the invention

[0003] The purpose of the present invention is to provide a method, device, equipment and readable storage medium for evaluating the safety of tunnel structures in mountainous areas to improve the above-mentioned problems. In order to achieve the above-mentioned purpose, the technical solutions adopted by the present invention are as follows:

[0004] In a first aspect, the present application provides a method for evaluating the structural safety of a mountain tunnel, comprising:

[0005] Obtain the safety evaluation index of the tunnel structure;

[0006] A number of samples are randomly generated within a preset safety level according to the safety evaluation index to obtain a constructed sample set, wherein the safety level is obtained by dividing the safety evaluation index by the spalling condition, cracking condition, water leakage condition and safety factor of the secondary lining in the tunnel structure;

[0007] Combining the most unfavorable reference values ​​of the safety evaluation indicators under the safety level to obtain a limit sample set;

[0008] Calculate the combined weight of each of the safety evaluation indicators based on group decision making, AHP algorithm, entropy weight method, CRITIC method and game theory;

[0009] Calculate the first proximity value of each extreme sample in the extreme sample set based on the TOPSIS decision method and the combined weight, calculate the second proximity value of each construction sample in the construction sample set based on the TOPSIS decision method and the combined weight, sort the first proximity values ​​to obtain the quantization interval of each security level, determine the quantization interval where each second proximity value is located, and obtain a training sample set;

[0010] A preset extreme learning machine is trained according to the training sample set to obtain a safety evaluation model, and sample data of the tunnel structure to be evaluated is input into the safety evaluation model for evaluation to obtain a safety evaluation result.

[0011] In a second aspect, the present application also provides a mountain tunnel structure safety evaluation device, comprising:

[0012] An acquisition module, the acquisition module is used to acquire a safety evaluation index of a tunnel structure;

[0013] A random generation module, the random generation module is used to randomly generate a number of samples within a preset safety level according to the safety evaluation index to obtain a construction sample set, wherein the safety level is obtained by dividing the safety evaluation index by the spalling condition, cracking condition, water leakage condition and safety factor of the secondary lining in the tunnel structure;

[0014] A combination module, the combination module is used to combine the most unfavorable reference values ​​of each of the safety evaluation indicators under the safety level to obtain a limit sample set;

[0015] A first calculation module, wherein the first calculation module is used to calculate the combined weight of each of the safety evaluation indicators based on group decision-making, AHP algorithm, entropy weight method, CRITIC method and game theory;

[0016] A second calculation module, the second calculation module is used to calculate the first proximity value of each extreme sample in the extreme sample set based on the TOPSIS decision method and the combined weight, calculate the second proximity value of each construction sample in the construction sample set based on the TOPSIS decision method and the combined weight, sort the first proximity values ​​to obtain the quantization interval of each security level, determine the quantization interval where each second proximity value is located, and obtain a training sample set;

[0017] An evaluation module is used to train a preset extreme learning machine according to the training sample set to obtain a safety evaluation model, input sample data of the tunnel structure to be evaluated into the safety evaluation model for evaluation, and obtain a safety evaluation result.

[0018] In a third aspect, the present application also provides a mountain tunnel structure safety evaluation device, comprising:

[0019] Memory for storing computer programs;

[0020] A processor is used to implement the steps of the mountain tunnel structure safety assessment method when executing the computer program.

[0021] In a fourth aspect, the present application further provides a readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the above-mentioned method for safety assessment of tunnel structures in mountainous areas are implemented.

[0022] The beneficial effects of the present invention are as follows: the present invention realizes the quantification of various safety evaluation indicators that affect the safety of tunnel structures in mountainous environments through a mountain tunnel structure safety evaluation method, device, equipment and readable storage medium, improves the accuracy of the evaluation indicator weight calculation, and can quickly and accurately evaluate the structural safety status of a certain mountain tunnel section.

[0023] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or be understood by implementing the embodiments of the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description, claims, and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0025] Figure 1 It is a schematic diagram of the flow chart of the method for evaluating the structure safety of a tunnel in a mountainous area described in an embodiment of the present invention;

[0026] Figure 2 A logical diagram of a method for evaluating the structural safety of a tunnel in a mountainous area described in an embodiment of the present invention;

[0027] Figure 3 It is a mountain tunnel structure safety evaluation index system in an embodiment of the present invention;

[0028] Figure 4 is the judgment matrix made by the experts for the evaluation indicators in the embodiment of the present invention;

[0029] Figure 5 It is a schematic diagram of the structure of a mountain tunnel structure safety evaluation device described in an embodiment of the present invention.

[0030] Markings in the figure: 800, mountain tunnel structure safety evaluation equipment; 801, processor; 802, memory; 803, multimedia component; 804, I / O interface; 805, communication component. DETAILED DESCRIPTION

[0031] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. The components of the embodiments of the present invention generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0032] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings. At the same time, in the description of the present invention, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0033] Embodiment 1:

[0034] This embodiment provides a method for evaluating the safety of tunnel structures in mountainous areas.

[0035] See also Figure 1 and Figure 2 , the figure shows that the method includes step S100, step S200, step S300, step S400, and step S500.

[0036] Step S100: obtaining a safety evaluation index of a tunnel structure;

[0037] Obtain the safety evaluation indicators of the tunnel structure, including:

[0038] Acquiring engineering geological characteristics, including modified rock mass basic quality indicators, rock uniaxial compressive strength, rock mass integrity, calculated water inflow, precipitation, and fault fracture zone impact of the tunnel structure;

[0039] Obtaining tunnel stress characteristics, wherein the tunnel stress characteristics include an angle between a tunnel axis and a principal stress direction, a geostress influence coefficient, and a secondary lining strength ratio of the tunnel structure;

[0040] Acquire tunnel structural characteristics, wherein the tunnel structural characteristics include secondary lining thickness, lining support type, cavern section span, and cavern section height-span ratio influence of the tunnel structure;

[0041] Obtain the service life, earthquake intensity and design and construction level of the tunnel structure.

[0042] like Figure 3 As shown in the figure, considering the factors that have a significant impact on the safety of tunnel structures in mountainous environments, engineering geological characteristics U1, tunnel stress characteristics U2, tunnel structural characteristics U3, and other influencing factors U4 are selected as the first-level indicators for safety evaluation. The second-level indicators of engineering geological characteristics include: modified rock mass basic quality index u 11 , uniaxial compressive strength of rock u 12 , rock mass integrity 13 , calculate the water inflow u 14 , precipitation 15 、Fault zone influence 16 The secondary indicators of tunnel stress characteristics include: the angle u between the tunnel axis and the principal stress direction 21 , Geostress influence coefficient u 22 , Second lining strength ratio u 23 ; The secondary indicators of tunnel structural characteristics include: secondary lining thickness u 31 , lining support type 32 、Cave section span u 33 、The influence of the height-span ratio of the cavern section u 34 ; Secondary indicators of other influencing factors include: service life u 41 、Earthquake intensity u 42 , design and construction level 43 .

[0043] Step S200: randomly generating a number of samples within a preset safety level according to the safety evaluation index to obtain a construction sample set, wherein the safety level is obtained by dividing the safety evaluation index by the spalling condition, cracking condition, water leakage condition and safety factor of the secondary lining in the tunnel structure;

[0044] According to the spalling, cracking, water leakage and safety factor of the secondary lining, the tunnel structure safety status is divided into four levels, namely I, II, III and IV. The higher the level, the less safe the surface structure is, and vice versa. The comment set is shown in Table 1 below:

[0045] Table 1

[0046]

[0047] The structural safety evaluation index benchmarks for mountain tunnels under four safety levels are shown in Table 2.

[0048] Table 2

[0049]

[0050] The unifrnd function of MATLAB software is used to randomly generate 800 samples that meet the actual engineering requirements within the evaluation index range to obtain a constructed sample set. Some data are shown in Table 3 below:

[0051] Table 3

[0052]

[0053] Step S300: combining the most unfavorable reference values ​​of the safety evaluation indicators under the safety level to obtain a limit sample set;

[0054] The most unfavorable benchmark values ​​of the combined tunnel structure evaluation indicators under the four safety levels are used to form an extreme sample set, as shown in Table 4 below:

[0055] Table 4

[0056]

[0057] Step S400: Calculate the combined weight of each of the safety evaluation indicators based on group decision making, AHP algorithm, entropy weight method, CRITIC method and game theory;

[0058] The step S400 specifically includes the following steps:

[0059] Obtaining a judgment matrix, wherein the judgment matrix is ​​a judgment matrix obtained by comparing the safety evaluation indicators in pairs according to the 1-9 scaling method by each expert;

[0060] Obtain the authority of each expert, which is a weighted sum of the weights of each authority influence factor and each authority score, wherein the authority influence factor includes the expert's honors, scientific research achievements, working time and degree qualifications;

[0061] Normalizing the authority;

[0062] According to the judgment matrix and the normalized authority, a weighted optimal transfer matrix is ​​calculated based on transfer matrix theory;

[0063] Calculating a comprehensive judgment matrix according to the weighted optimal transfer matrix and the exponential function;

[0064] Calculating the subjective weight of each of the safety evaluation indicators based on the column sum inversion method according to the comprehensive judgment matrix;

[0065] Performing standardization processing on the constructed sample set to obtain standardized data;

[0066] Calculate the entropy value of each of the safety evaluation indicators according to the standardized data;

[0067] Calculate the standard deviation of the construction sample corresponding to each of the safety evaluation indicators according to the standardized data, calculate the Pearson coefficient of each of the safety evaluation indicators according to the standard deviation, and calculate the conflict parameter of each of the safety evaluation indicators according to the Pearson coefficient, wherein the conflict parameter is used to reflect the conflict between each of the safety evaluation indicators and all other safety evaluation indicators;

[0068] The objective weight of each of the safety evaluation indicators is calculated according to the entropy value, standard deviation, conflict parameter and the total number of the safety evaluation indicators. The objective weight calculation formula is as follows:

[0069]

[0070] I t =(S t -E t )Q t

[0071]

[0072] In the above formula, I t represents the information amount of the tth safety evaluation index, the S t is the standard deviation of the tth safety evaluation index, Q t represents the conflict parameter of the tth safety evaluation index, W o is the objective weight, v represents the total number of the safety evaluation indicators, r pt is the Pearson coefficient between the p-th safety evaluation index and the t-th safety evaluation index, E t ) is the entropy value;

[0073] Constructing a linear combination of the subjective weight and the objective weight according to the subjective weight, the objective weight, the subjective weight coefficient and the objective weight coefficient;

[0074] A countermeasure model is established with the subjective weight coefficient and the objective weight coefficient being minimized as the optimization goal, and the first-order derivative of the optimization of the countermeasure model is simplified to obtain a linear equation system;

[0075] The linear equations are solved to obtain the combination weights.

[0076] To determine the subjective weight, we need to first assume that for the tunnel structure safety evaluation index, n experts are invited to participate in the consultation. The experts compare the m evaluation indicators in pairs according to the 1-9 scaling method and give the judgment matrix: A1, A2, A3, …, A n .

[0077] Combined with the expert authority, we consider the four influential factors of experts in this field: honors, scientific research achievements, working time, and degree. Then the authority score of the kth expert is B k for:

[0078] B k =α1b1+α2b2+α3b3+α4b4(k=1,2,…n)

[0079] In the formula, α i and b i They represent the weights and single factor scores of the four influential factors respectively, where α i ∈[0,1], b i ∈[0,100], i=1,2,3,4.

[0080] Then normalize the expert authority to get the authority C of the kth expert. k for:

[0081]

[0082] Judgment Matrix is a reciprocal matrix, let:

[0083]

[0084] Represents the judgment matrix A k The element in row i and column j of ;

[0085] Then D k is an antisymmetric matrix. According to the transfer matrix theory and combined with the expert authority, the weighted optimal transfer matrix P can be obtained as (p ij ) m×m :

[0086]

[0087] p ij represents the element in the i-th row and j-th column of the weighted optimal transfer matrix, Represents the judgment matrix A k The element in row i and column l in Represents the judgment matrix A k The element at row j and column l in ;

[0088] A comprehensive judgment matrix A generated by group decision-making of multiple experts based on evaluation indicators * It can be expressed as:

[0089]

[0090] The column sum inversion method is used to calculate the exact solution W of the weights of each indicator under the comprehensive judgment matrix. s :

[0091]

[0092] w1,…,w m ) represent the subjective weights of the 1st...mth indicators, Represents the comprehensive judgment matrix Α * The element in row i and column 1, Represents the comprehensive judgment matrix Α * The element in the i-th row and m-th column;

[0093] For constructing the sample set matrix X, assuming that the sample has u objects to be evaluated and v evaluation indicators, the data sample matrix X is:

[0094]

[0095] In order to eliminate the impact of the difference in the dimensions of different indicators, the positive indicators, reverse indicators and optimal indicators at a certain point in the data sample are standardized respectively: The formula for normalization of positive indicator data is:

[0096]

[0097] Reverse indicator data standardization formula:

[0098]

[0099] The optimal data normalization formula for a certain point:

[0100]

[0101] In the formula, x st Safety evaluation index of item t Next s sample data, x 1t ,...,x ut For the tth item Safety evaluation indicators Next 1..r.ut sample data , x' st is the sth sample data under the tth safety evaluation index after standardization, r st It represents the optimal original data positive of the sth sample under the tth safety evaluation index After the data is transformed, 1t ,...,r ut In order The data after the 1st to r.utth sample optimal original data under the tth safety evaluation index are forward-converted. a represents the optimal point in the optimal original data at a certain point. δ is the correction coefficient to avoid the inability to calculate the entropy value due to the generation of 0 value, which is taken as 0.1.

[0102] After standardization, calculate the proportion of each sample data in the column and y under each indicator st , thereby calculating the entropy value E of each evaluation index t :

[0103]

[0104]

[0105] The sample standard deviation S of the data under each indicator is used t To characterize the volatility of the t-th safety evaluation index, the Pearson coefficient r is used to reflect the correlation between the indicators, Q t Reflects the conflict between the tth safety evaluation index and all other indicators. The calculation formula is as follows:

[0106]

[0107]

[0108]

[0109] In the formula, is the mean value of the t-th safety evaluation index column after standardization, cov(x' p ,x t ') is the covariance between the pth index and the tth index, S p and S t are the sample standard deviations of the p-th indicator and the t-th indicator, respectively, where p = 1, 2, …, v.

[0110] Calculate the information content of the indicator I t , and calculate the objective weight W o :

[0111] I t =(S t -E t )Q t

[0112]

[0113] w1,w2,…,w v They represent the objective weights of the 1st, 2nd, …, vth safety evaluation indicators respectively;

[0114] According to the properties of the evaluation indicators (positive index, negative index, and optimality index at a certain point), the data at the constructed sample level is standardized to eliminate the impact of different dimensions of the evaluation indicators and obtain a standardized data sample set. Combining the respective advantages of the entropy weight method (EMW) and the CRITIC method, the objective weight calculation is more comprehensive through the three types of laws: discrete degree, volatility, and conflict.

[0115] The basic idea of ​​using game theory to scientifically combine weights is to minimize the deviation between the final weight distribution of each indicator and the weight obtained by each method, so as to make the weight distribution obtained by multiple methods more reasonable.

[0116] Set the linear combination of the indicator weight vectors obtained by the two weighting methods:

[0117] W * =α s W s +α o W o

[0118] In the formula, α s ,α o They represent the weight coefficients of the two weighting methods: subjective weighting and objective weighting.

[0119] The two linear combination coefficients are optimized with the goal of minimizing the deviation, a countermeasure model is established, and the first-order derivative of the optimal countermeasure model is simplified to obtain the following linear equations:

[0120]

[0121] Solve and normalize the optimal linear combination coefficients to obtain the combined weight set W based on game theory * :

[0122]

[0123]

[0124] In the formula, Respectively represent the normalized optimal weight coefficients of the two weighting methods.

[0125] The weights of each evaluation index are calculated and shown in Table 5:

[0126] Table 5

[0127]

[0128] Step S500: Calculate the first proximity value of each extreme sample in the extreme sample set based on the TOPSIS decision method and the combined weight, calculate the second proximity value of each construction sample in the construction sample set based on the TOPSIS decision method and the combined weight, sort the first proximity values ​​to obtain the quantization interval of each security level, determine the quantization interval where each second proximity value is located, and obtain a training sample set.

[0129] Step S500 specifically includes:

[0130] Performing standardization processing on the extreme sample set to obtain a first matrix;

[0131] Performing weighted processing on the first matrix to obtain a standardized limit sample set;

[0132] Calculate the positive ideal solution and the negative ideal solution of the standardized limit sample set, wherein the positive ideal solution is a sample that maximizes the positive index and minimizes the negative index, and the negative ideal solution is a sample that minimizes the positive index and maximizes the negative index;

[0133] Respectively calculate the first Euclidean distance and the second Euclidean distance of each sample in the standardized limit sample set to the positive ideal solution and the negative ideal solution of the standardized limit sample set;

[0134] Calculate the first proximity value according to the first Euclidean distance and the second Euclidean distance;

[0135] Performing standardization processing on the constructed sample set to obtain a second matrix;

[0136] Performing weighted processing on the second matrix to obtain a standardized construction sample set;

[0137] Calculate the positive and negative ideal solutions of the standardized constructed sample set;

[0138] Respectively calculating the third Euclidean distance and the fourth Euclidean distance of each sample in the standardized constructed sample set to the positive ideal solution and the negative ideal solution of the standardized constructed sample set;

[0139] The second proximity value is calculated according to the third Euclidean distance and the fourth Euclidean distance.

[0140] The TOPSIS decision model, or the method of ranking by approximate ideal solutions, is an analytical model for multi-criteria decision making. It determines the "positive ideal solution" and the "negative ideal solution" and ranks the alternative solutions according to the degree of proximity between the alternative solutions and the ideal solution.

[0141] Calculate the ideal solution. The ideal solution is divided into positive ideal solution and negative ideal solution. The positive ideal solution refers to the sample that maximizes the positive index and minimizes the negative index:

[0142] f t + =[(maxf st |f t ∈Ω b ),(minf st |f t ∈Ω c )]

[0143] The negative ideal solution refers to the sample that minimizes the positive index and maximizes the negative index:

[0144] f t - =[(minf st |f t ∈Ω b ),(maxf st |f t ∈Ω c )]

[0145] In the formula, f t + represents the positive ideal solution of the tth evaluation index, f t represents the tth evaluation index; f st represents the tth evaluation index of the sth solution, Ω b Represents a positive indicator, Ω c Represents a negative indicator, f t - represents the negative ideal solution of the tth evaluation index.

[0146] Calculate the Euclidean distance of each evaluation sample to the positive and negative ideal solutions:

[0147]

[0148]

[0149] Calculate the first proximity G s , whose expression is:

[0150]

[0151] In the formula, G s ∈[0,1],G s The closer the value is to 1, the closer the safety of the sample is to level IV safety, and the closer the value is to 0, the closer the safety of the sample is to level I safety.

[0152] The quantization intervals of each security level based on proximity are determined by sorting, as shown in Table 6 below:

[0153] Table 6

[0154] Security Level Quantization interval based on first proximity I (0.000,0.312] II (0.312,0.589] III (0.589,0.791] IV (0.791,1.000)

[0155] Similarly, the second proximity value of each constructed sample is calculated based on the TOPSIS decision model, and the quantization interval of the second proximity value is determined to determine the security level, and the security level of the constructed sample set is obtained, that is, the training label for machine learning, so as to convert the constructed sample set into the training sample set, as shown in Table 7:

[0156] Table 7

[0157]

[0158] Step S600: Train a preset extreme learning machine according to the training sample set to obtain a safety evaluation model, input the sample data of the tunnel structure to be evaluated into the safety evaluation model for evaluation, and obtain a safety evaluation result. The extreme learning machine randomly generates the connection weights between the input layer and the hidden layer and the thresholds of the hidden layer neurons, and does not need to be adjusted during the training process. It only needs to set the number of hidden layer neurons to obtain a unique optimal solution. Compared with traditional training methods, this method has the advantages of fast learning speed and good generalization performance.

[0159] Embodiment 2:

[0160] This embodiment provides a device for evaluating the safety of a tunnel structure in a mountainous area, the device comprising:

[0161] An acquisition module, the acquisition module is used to acquire a safety evaluation index of a tunnel structure;

[0162] A random generation module, the random generation module is used to randomly generate a number of samples within a preset safety level according to the safety evaluation index to obtain a construction sample set, wherein the safety level is obtained by dividing the safety evaluation index by the spalling condition, cracking condition, water leakage condition and safety factor of the secondary lining in the tunnel structure;

[0163] A combination module, the combination module is used to combine the most unfavorable reference values ​​of each of the safety evaluation indicators under the safety level to obtain a limit sample set;

[0164] A first calculation module, wherein the first calculation module is used to calculate the combined weight of each of the safety evaluation indicators based on group decision-making, AHP algorithm, entropy weight method, CRITIC method and game theory;

[0165] A second calculation module, the second calculation module is used to calculate the first proximity value of each extreme sample in the extreme sample set based on the TOPSIS decision method and the combined weight, calculate the second proximity value of each construction sample in the construction sample set based on the TOPSIS decision method and the combined weight, sort the first proximity values ​​to obtain the quantization interval of each security level, determine the quantization interval where each second proximity value is located, and obtain a training sample set;

[0166] An evaluation module is used to train a preset extreme learning machine according to the training sample set to obtain a safety evaluation model, input sample data of the tunnel structure to be evaluated into the safety evaluation model for evaluation, and obtain a safety evaluation result.

[0167] The first calculation module includes:

[0168] A first acquisition module, the first acquisition module is used to acquire a judgment matrix, the judgment matrix is ​​a judgment matrix obtained by each expert comparing the safety evaluation indicators in pairs according to a 1-9 scaling method;

[0169] A second acquisition module, which is used to obtain the authority of each expert, wherein the authority is a weighted sum of the weights of each authority influence factor and each authority score, wherein the authority influence factor includes the expert's honors, scientific research achievements, working time and degree qualifications;

[0170] A normalization module, the normalization module is used to perform normalization processing on the authority;

[0171] A third calculation module, the third calculation module is used to calculate a weighted optimal transfer matrix based on the judgment matrix and the normalized authority and based on the transfer matrix theory;

[0172] A fourth calculation module, the fourth calculation module is used to calculate a comprehensive judgment matrix according to the weighted optimal transfer matrix and the exponential function;

[0173] A fifth calculation module is used to calculate the subjective weight of each of the safety evaluation indicators based on the column sum inversion method according to the comprehensive judgment matrix.

[0174] The first calculation module includes:

[0175] A standardization module, wherein the standardization module is used to perform standardization processing on the constructed sample set to obtain standardized data;

[0176] A sixth calculation module, the sixth calculation module is used to calculate the entropy value of each of the safety evaluation indicators according to the standardized data;

[0177] A seventh calculation module, the seventh calculation module is used to calculate the standard deviation of the corresponding construction sample under each of the safety evaluation indicators according to the standardized data, calculate the Pearson coefficient of each of the safety evaluation indicators according to the standard deviation, and calculate the conflict parameter of each of the safety evaluation indicators according to the Pearson coefficient, wherein the conflict parameter is used to reflect the conflict between each of the safety evaluation indicators and all other safety evaluation indicators;

[0178] An eighth calculation module, the eighth calculation module is used to calculate the objective weight of each of the security evaluation indicators according to the entropy value, standard deviation, conflict parameter and the total number of the security evaluation indicators.

[0179] The first calculation module includes:

[0180] A construction module, the construction module is used to construct a linear combination of the subjective weight and the objective weight according to the subjective weight, the objective weight, the subjective weight coefficient and the objective weight coefficient;

[0181] An establishment module, wherein the establishment module is used to establish a countermeasure model with the subjective weight coefficient and the objective weight coefficient being minimized by deviation as the optimization goal, and simplify the first-order derivative of the optimization of the countermeasure model to obtain a linear equation system;

[0182] A solution module is used to solve the linear equations to obtain the combination weight.

[0183] It should be noted that, regarding the device in the above embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment of the method, and will not be elaborated here.

[0184] Embodiment 3:

[0185] Corresponding to the above method embodiment, this embodiment also provides a mountain tunnel structure safety evaluation device. The mountain tunnel structure safety evaluation device described below and the mountain tunnel structure safety evaluation method described above can refer to each other.

[0186] Figure 5 FIG. 8 is a block diagram of a mountain tunnel structure safety evaluation device 800 according to an exemplary embodiment. Figure 5 As shown, the mountain tunnel structure safety evaluation device 800 may include: a processor 801 and a memory 802. The mountain tunnel structure safety evaluation device 800 may also include one or more of a multimedia component 803, an I / O interface 804, and a communication component 805.

[0187] The processor 801 is used to control the overall operation of the mountain tunnel structure safety evaluation device 800 to complete all or part of the steps in the mountain tunnel structure safety evaluation method. The memory 802 is used to store various types of data to support the operation of the mountain tunnel structure safety evaluation device 800, which may include, for example, instructions for any application or method operating on the mountain tunnel structure safety evaluation device 800, and application-related data, such as contact data, sent and received messages, pictures, audio, video, etc. The memory 802 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, disk or optical disk. The multimedia component 803 may include a screen and an audio component. The screen may be, for example, a touch screen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signal may be further stored in the memory 802 or sent via the communication component 805. The audio component also includes at least one speaker for outputting audio signals. The I / O interface 804 provides an interface between the processor 801 and other interface modules, and the above-mentioned other interface modules can be keyboards, mice, buttons, etc. These buttons can be virtual buttons or physical buttons. The communication component 805 is used for wired or wireless communication between the mountain tunnel structure safety evaluation device 800 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G or 4G, or a combination of one or more of them, so the corresponding communication component 805 can include: Wi-Fi module, Bluetooth module, NFC module.

[0188] In an exemplary embodiment, the mountain tunnel structure safety evaluation device 800 can be implemented by one or more application specific integrated circuits (Application Specific Integrated Circuit, referred to as ASIC), digital signal processors (Digital Signal Processor, referred to as DSP), digital signal processing devices (Digital Signal Processing Device, referred to as DSPD), programmable logic devices (Programmable Logic Device, referred to as PLD), field programmable gate arrays (Field Programmable Gate Array, referred to as FPGA), controllers, microcontrollers, microprocessors or other electronic components to execute the above-mentioned mountain tunnel structure safety evaluation method.

[0189] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, and when the program instructions are executed by a processor, the steps of the above-mentioned mountain tunnel structure safety evaluation method are implemented. For example, the computer-readable storage medium can be the above-mentioned memory 802 including program instructions, and the above-mentioned program instructions can be executed by the processor 801 of the mountain tunnel structure safety evaluation device 800 to complete the above-mentioned mountain tunnel structure safety evaluation method.

[0190] Embodiment 4:

[0191] Corresponding to the above method embodiment, a readable storage medium is also provided in this embodiment. The readable storage medium described below and the mountain tunnel structure safety evaluation method described above can refer to each other.

[0192] A readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the mountain tunnel structure safety assessment method of the above method embodiment.

[0193] The readable storage medium may specifically be a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, or other readable storage medium that can store program codes.

[0194] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

[0195] Example 5

[0196] For some tunnel sections in the dangerous mountainous areas in the west, by investigating a large amount of on-site survey data and design information, the engineering geological characteristics, tunnel stress characteristics, tunnel structure characteristics, and relevant data of secondary indicators under other influencing factors of these tunnel projects were determined, and sample data of the tunnel sections to be evaluated were obtained. Some of the data are shown in Table 8 below:

[0197] Table 8

[0198]

[0199] For the above-mentioned sample set of mountain tunnel sections to be evaluated, the actual safety level of each section is determined one by one according to the comment set, and the actual safety status of the tunnel section samples is obtained. In addition, the mountain tunnel structure safety evaluation model based on knowledge decision-making and data analysis that has been trained by the present invention is used to evaluate each, and the evaluation accuracy rate reaches 91.3%, which can realize the rapid and accurate evaluation of the structural safety status of a certain mountain tunnel section. Some evaluation results are shown in Table 9;

[0200] Table 9

[0201]

[0202] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for evaluating the structural safety of a mountain tunnel, characterized in that: include: Obtain the safety evaluation index of the tunnel structure; A number of samples are randomly generated within a preset safety level according to the safety evaluation index to obtain a constructed sample set, wherein the safety level is obtained by dividing the safety evaluation index by the spalling condition, cracking condition, water leakage condition and safety factor of the secondary lining in the tunnel structure; Combining the most unfavorable reference values ​​of the safety evaluation indicators under the safety level to obtain a limit sample set; Calculate the combined weight of each of the safety evaluation indicators based on group decision making, AHP algorithm, entropy weight method, CRITIC method and game theory; Calculate the first proximity value of each extreme sample in the extreme sample set based on the TOPSIS decision method and the combined weight, calculate the second proximity value of each construction sample in the construction sample set based on the TOPSIS decision method and the combined weight, sort the first proximity values ​​to obtain the quantization interval of each security level, determine the quantization interval where each second proximity value is located, and obtain a training sample set; A preset extreme learning machine is trained according to the training sample set to obtain a safety evaluation model, and sample data of the tunnel structure to be evaluated is input into the safety evaluation model for evaluation to obtain a safety evaluation result.

2. The method for evaluating the structural safety of a mountain tunnel according to claim 1, characterized in that: The combined weights of the safety evaluation indicators are calculated based on group decision making, AHP algorithm, entropy weight method, CRITIC method and game theory, including: As shown in FIG4 , a judgment matrix is ​​obtained, wherein the judgment matrix is ​​a judgment matrix obtained by comparing the safety evaluation indicators in pairs according to the 1-9 scaling method by each expert; Obtain the authority of each expert, which is a weighted sum of the weights of each authority influence factor and each authority score, wherein the authority influence factor includes the expert's honors, scientific research achievements, working time and degree qualifications; Normalizing the authority; According to the judgment matrix and the normalized authority, a weighted optimal transfer matrix is ​​calculated based on transfer matrix theory; Calculating a comprehensive judgment matrix according to the weighted optimal transfer matrix and the exponential function; The subjective weight of each of the safety evaluation indicators is calculated based on the column sum inversion method according to the comprehensive judgment matrix.

3. The method for evaluating the structural safety of a mountain tunnel according to claim 2, characterized in that: The combined weights of the safety evaluation indicators are calculated based on group decision making, AHP algorithm, entropy weight method, CRITIC method and game theory, including: Performing standardization processing on the constructed sample set to obtain standardized data; Calculate the entropy value of each of the safety evaluation indicators according to the standardized data; Calculate the standard deviation of the construction sample corresponding to each of the safety evaluation indicators according to the standardized data, calculate the Pearson coefficient of each of the safety evaluation indicators according to the standard deviation, and calculate the conflict parameter of each of the safety evaluation indicators according to the Pearson coefficient, wherein the conflict parameter is used to reflect the conflict between each of the safety evaluation indicators and all other safety evaluation indicators; The objective weight of each of the safety evaluation indicators is calculated according to the entropy value, the standard deviation, the conflict parameter and the total number of the safety evaluation indicators.

4. The method for evaluating the structural safety of a mountain tunnel according to claim 3 is characterized in that: The combined weights of the safety evaluation indicators are calculated based on group decision making, AHP algorithm, entropy weight method, CRITIC method and game theory, including: Constructing a linear combination of the subjective weight and the objective weight according to the subjective weight, the objective weight, the subjective weight coefficient and the objective weight coefficient; A countermeasure model is established with the subjective weight coefficient and the objective weight coefficient being minimized as the optimization goal, and the first-order derivative of the optimization of the countermeasure model is simplified to obtain a linear equation system; The linear equations are solved to obtain the combination weights.

5. A mountain tunnel structure safety evaluation device, characterized in that: include: An acquisition module, the acquisition module is used to acquire a safety evaluation index of a tunnel structure; A random generation module, the random generation module is used to randomly generate a number of samples within a preset safety level according to the safety evaluation index to obtain a construction sample set, wherein the safety level is obtained by dividing the safety evaluation index by the spalling condition, cracking condition, water leakage condition and safety factor of the secondary lining in the tunnel structure; A combination module, the combination module is used to combine the most unfavorable reference values ​​of each of the safety evaluation indicators under the safety level to obtain a limit sample set; A first calculation module, wherein the first calculation module is used to calculate the combined weight of each of the safety evaluation indicators based on group decision-making, AHP algorithm, entropy weight method, CRITIC method and game theory; A second calculation module, the second calculation module is used to calculate the first proximity value of each extreme sample in the extreme sample set based on the TOPSIS decision method and the combined weight, calculate the second proximity value of each construction sample in the construction sample set based on the TOPSIS decision method and the combined weight, sort the first proximity values ​​to obtain the quantization interval of each security level, determine the quantization interval where each second proximity value is located, and obtain a training sample set; An evaluation module is used to train a preset extreme learning machine according to the training sample set to obtain a safety evaluation model, input sample data of the tunnel structure to be evaluated into the safety evaluation model for evaluation, and obtain a safety evaluation result.

6. The mountain tunnel structure safety evaluation device according to claim 5 is characterized in that: The first calculation module includes: A first acquisition module, the first acquisition module is used to acquire a judgment matrix, the judgment matrix is ​​a judgment matrix obtained by each expert comparing the safety evaluation indicators in pairs according to a 1-9 scaling method; A second acquisition module, which is used to obtain the authority of each expert, wherein the authority is a weighted sum of the weights of each authority influence factor and each authority score, wherein the authority influence factor includes the expert's honors, scientific research achievements, working time and degree qualifications; A normalization module, the normalization module is used to perform normalization processing on the authority; A third calculation module, the third calculation module is used to calculate a weighted optimal transfer matrix based on the judgment matrix and the normalized authority and based on the transfer matrix theory; A fourth calculation module, the fourth calculation module is used to calculate a comprehensive judgment matrix according to the weighted optimal transfer matrix and the exponential function; A fifth calculation module is used to calculate the subjective weight of each of the safety evaluation indicators based on the column sum inversion method according to the comprehensive judgment matrix.

7. The mountain tunnel structure safety evaluation device according to claim 6 is characterized in that: The first calculation module includes: A standardization module, wherein the standardization module is used to perform standardization processing on the constructed sample set to obtain standardized data; A sixth calculation module, the sixth calculation module is used to calculate the entropy value of each of the safety evaluation indicators according to the standardized data; A seventh calculation module, the seventh calculation module is used to calculate the standard deviation of the corresponding construction sample under each of the safety evaluation indicators according to the standardized data, calculate the Pearson coefficient of each of the safety evaluation indicators according to the standard deviation, and calculate the conflict parameter of each of the safety evaluation indicators according to the Pearson coefficient, wherein the conflict parameter is used to reflect the conflict between each of the safety evaluation indicators and all other safety evaluation indicators; An eighth calculation module, the eighth calculation module is used to calculate the objective weight of each of the security evaluation indicators according to the entropy value, standard deviation, conflict parameter and the total number of the security evaluation indicators.

8. The mountain tunnel structure safety evaluation device according to claim 7 is characterized in that: The first calculation module includes: A construction module, the construction module is used to construct a linear combination of the subjective weight and the objective weight according to the subjective weight, the objective weight, the subjective weight coefficient and the objective weight coefficient; An establishment module, wherein the establishment module is used to establish a countermeasure model with the subjective weight coefficient and the objective weight coefficient being minimized by deviation as the optimization goal, and simplify the first-order derivative of the optimization of the countermeasure model to obtain a linear equation system; A solution module is used to solve the linear equations to obtain the combination weight.

9. A mountain tunnel structure safety evaluation device, characterized in that: include: Memory for storing computer programs; A processor is used to implement the steps of the mountain tunnel structure safety assessment method as claimed in any one of claims 1 to 4 when executing the computer program.

10. A readable storage medium, characterized in that: The readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the method for safety assessment of mountain tunnel structure as claimed in any one of claims 1 to 4.

Images