Tunnel construction safety assessment method, device and equipment based on Bayesian grey cloud model, medium and product

Abstract

The invention discloses a tunnel construction safety assessment method and device based on a Bayesian grey cloud model, equipment, a medium and a product, and relates to the field of tunnel safety assessment, and the method comprises the steps: constructing an assessment index system for tunnel construction safety assessment; collecting the data of each secondary index in the tunnel construction process in the current period, and determining the danger level of each secondary index based on the data of each secondary index; determining the grey number range of each secondary index according to the danger level of each secondary index; according to the grey number range, a grey cloud model is adopted to calculate the correlation degree of each first-level index and the tunnel construction in different safety states; the safety state comprises safety, general and danger; and based on the correlation degree, evaluating the tunnel construction safety by adopting a Bayesian algorithm to obtain an evaluation result of the tunnel construction safety in the current period. According to the invention, the accuracy of tunnel construction safety assessment is improved.

Description

Technical Field

[0001] The present application relates to the field of tunnel safety assessment, and in particular to a tunnel construction safety assessment method, device, equipment, medium and product based on a Bayesian ash cloud model. Background Art

[0002] Tunnel construction environments are complex, involving numerous factors that affect safety, such as personnel operations, equipment operation, and geological conditions. Tunnel safety assessments often involve a large number of indicators, primarily qualitative and quantitative. However, qualitative indicators are often subject to subjective factors, such as geological survey information and construction information, and their accuracy needs to be further improved. Furthermore, the qualitative assessments of certain construction and management experts are also subject to subjective factors. Consequently, many assessment indicators cannot be accurately described numerically, resulting in low assessment accuracy. As tunnel projects increase in scale and complexity, higher requirements are placed on the accuracy and reliability of safety assessment methods. Currently, existing assessment methods, such as the Analytic Hierarchy Process (AHP) and cloud models, struggle to effectively handle the complex and uncertain information inherent in construction and cannot fully integrate multiple indicators. Summary of the Invention

[0003] The purpose of this application is to provide a tunnel construction safety assessment method, device, equipment, medium and product based on the Bayesian ash cloud model, which can evaluate tunnel construction safety in combination with multi-source indicators and improve the accuracy of tunnel construction safety assessment.

[0004] To achieve the above objectives, this application provides the following solutions:

[0005] In a first aspect, the present application provides a tunnel construction safety assessment method based on a Bayesian ash cloud model, comprising:

[0006] Constructing an evaluation index system for tunnel construction safety assessment; the evaluation index system includes multiple first-level indicators, each of which includes multiple second-level indicators;

[0007] Collect data on each secondary indicator during the current tunnel construction process, and determine the danger level of each secondary indicator based on the data;

[0008] Determine the gray number range of each secondary indicator according to the danger level of each secondary indicator;

[0009] Based on the range of gray numbers, the gray cloud model is used to calculate the correlation between each primary indicator and the different safety states of tunnel construction; the safety states include safe, general and dangerous;

[0010] Based on the correlation degree, the Bayesian algorithm is used to evaluate the tunnel construction safety and obtain the evaluation results of the tunnel construction safety in the current period.

[0011] In a second aspect, the present application provides a tunnel construction safety assessment device based on a Bayesian ash cloud model, comprising:

[0012] A first building module is used to construct an evaluation index system for tunnel construction safety assessment; the evaluation index system includes multiple first-level indicators, and each first-level indicator includes multiple second-level indicators;

[0013] A hazard level determination module is used to collect data on various secondary indicators during the tunnel construction process during the current period and determine the hazard level of each secondary indicator based on the data of each secondary indicator;

[0014] A gray number range determination module is used to determine the gray number range of each secondary indicator according to the danger level of each secondary indicator;

[0015] The correlation calculation module is used to calculate the correlation between each primary indicator and the different safety states of tunnel construction based on the gray number range using the gray cloud model; the safety states include safe, general and dangerous;

[0016] The evaluation module is used to evaluate the tunnel construction safety based on the correlation degree and adopt the Bayesian algorithm to obtain the tunnel construction safety evaluation results for the current period.

[0017] In a third aspect, the present application provides a computer device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of any one of the above-mentioned tunnel construction safety assessment methods based on the Bayesian ash cloud model.

[0018] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any one of the above-mentioned tunnel construction safety assessment methods based on the Bayesian ash cloud model.

[0019] In a fifth aspect, the present application provides a computer program product, comprising a computer program, which, when executed by a processor, implements the steps of any one of the above-mentioned tunnel construction safety assessment methods based on the Bayesian ash cloud model.

[0020] According to the specific embodiments provided in this application, this application discloses the following technical effects:

[0021] The present application provides a tunnel construction safety assessment method, device, equipment, medium and product based on the Bayesian gray cloud model. By constructing an evaluation index system for tunnel construction safety assessment, each secondary indicator is quantified using a gray number range. The gray number range can be used to accurately quantify the qualitative indicators. On this basis, the gray cloud model is used to calculate the correlation between each primary indicator and the tunnel construction in different safety states. Multi-source indicators are comprehensively utilized, and then the Bayesian algorithm is used to evaluate the tunnel construction safety. A comprehensive evaluation of tunnel construction safety is achieved by combining multi-source indicators, thereby objectively and accurately evaluating the tunnel construction safety and improving the accuracy of the tunnel construction safety assessment. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0023] Figure 1 This is an application environment diagram of a tunnel construction safety assessment method based on a Bayesian ash cloud model in one embodiment of the present application;

[0024] Figure 2 A schematic diagram of a flow chart of a tunnel construction safety assessment method based on a Bayesian ash cloud model provided in one embodiment of the present application;

[0025] Figure 3 A schematic diagram illustrating the relationship between various indicators in the evaluation index system for tunnel construction safety evaluation provided in one embodiment of the present application;

[0026] Figure 4 A schematic diagram of a process for constructing an evaluation index system for tunnel construction safety assessment provided in one embodiment of the present application;

[0027] Figure 5 A schematic diagram of the functional modules of a tunnel construction safety assessment device based on a Bayesian ash cloud model provided in one embodiment of the present application;

[0028] Figure 6 A schematic diagram of the structure of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0029] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0030] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0031] The tunnel construction safety assessment method based on the Bayesian ash cloud model provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store data that server 104 needs to process. The data storage system can be provided separately, integrated with server 104, or located in the cloud or on another server. Terminal 102 can send data on each secondary indicator during the current tunnel construction period to server 104. Server 104 receives the data on each secondary indicator during the current tunnel construction period and constructs an evaluation index system for tunnel construction safety assessment. The evaluation index system includes multiple primary indicators, each of which includes multiple secondary indicators. Data on each secondary indicator during the current tunnel construction period is collected and, based on the data, a hazard level for each secondary indicator is determined. A gray number range for each secondary indicator is determined based on the hazard level. Based on the gray number range, a gray cloud model is used to calculate the correlation between each primary indicator and different safety states of the tunnel construction. Safety states include safe, general, and dangerous. Based on the correlation, a Bayesian algorithm is used to assess tunnel construction safety, obtaining an assessment result for tunnel construction safety during the current period. Server 104 can provide feedback to terminal 102 on the assessment result for tunnel construction safety during the current period. In addition, in some embodiments, the tunnel construction safety assessment method based on the Bayesian gray cloud model can also be implemented independently by the server 104 or the terminal 102. For example, the terminal 102 can directly process the data of each secondary indicator in the current period of tunnel construction process, or the server 104 can obtain the data of each secondary indicator in the current period of tunnel construction process from the data storage system for processing.

[0032] Terminal 102 may include, but is not limited to, various desktop computers, laptops, smartphones, tablet computers, IoT devices, and portable wearable devices. IoT devices may include smart speakers, smart TVs, smart air conditioners, and smart car devices. Portable wearable devices may include smart watches, smart bracelets, and head-mounted devices. Server 104 may be implemented as a standalone server or a server cluster consisting of multiple servers, or may be a cloud server.

[0033] In an exemplary embodiment, Figure 2 As shown, a tunnel construction safety assessment method based on the Bayesian ash cloud model is provided. The method is executed by a computer device, specifically a computer device such as a terminal or a server, or a terminal and a server. In the embodiment of the present application, the method is applied to Figure 1 The server 104 in the example is used as an example to illustrate the process, including the following steps 201 to 205.

[0034] Step 201 : constructing an evaluation index system for tunnel construction safety evaluation; the evaluation index system includes a plurality of first-level indicators, and each first-level indicator includes a plurality of second-level indicators.

[0035] like Figure 3 As shown in the figure, the first-level index of the tunnel construction safety assessment index R includes the geological factor index R1, the construction factor index R2 and the management factor index R3; the second-level index of the geological factor index R1 includes the surrounding rock grade index R 11 , lithologic characteristic index R 12 , surrounding rock grade index R 13 and lithologic characteristic index R 14 The secondary indicators in the construction factor index R2 include the tunnel length index R 21 , Tunnel excavation span index R 22 , one-time excavation footage index R 23 , advanced geological prediction index R 24 , monitoring measurement indicators R 25 , support effect index R 26 and tunnel depth index R 27 The secondary indicators in the management factor index R3 include the on-site safety system index R 31 , Engineering data completeness index R 32 , Risk control capability index R 33 , the surrounding residents' response index R34 and the project funding index R 35 .

[0036] Step 202 : collecting data of each secondary indicator during the tunnel construction process in the current period, and determining the danger level of each secondary indicator based on the data of each secondary indicator.

[0037] Step 203: determining the gray number range of each secondary indicator according to the danger level of each secondary indicator.

[0038] Step 204 , based on the gray number range, the gray cloud model is used to calculate the correlation between each first-level indicator and the different safety states of the tunnel construction; the safety states include safe, general, and dangerous.

[0039] Step 205 : Based on the correlation degree, the Bayesian algorithm is used to evaluate the tunnel construction safety, and an evaluation result of the tunnel construction safety in the current period is obtained.

[0040] By implementing the above steps 201 to 205 and combining multiple source indicators to evaluate the tunnel construction safety, the accuracy of the tunnel construction safety evaluation is improved.

[0041] In an exemplary embodiment, Figure 4 As shown, after determining the main factors affecting tunnel construction safety, an evaluation index system for tunnel construction safety assessment is constructed using each factor. The process of constructing the evaluation index system for tunnel construction safety assessment in step 201 includes:

[0042] (1) Data preprocessing

[0043] The data of each secondary indicator during the tunnel construction process at different periods are collected, and the collected data of the secondary indicators are preprocessed to obtain the digital characteristics of the data of each secondary indicator.

[0044] The cloud model is an uncertainty conversion model between a qualitative concept expressed in language values and its quantitative representation. It is characterized by three numerical characteristics of the cloud: expectation (Ex), entropy (En) and hyperentropy (He).

[0045] (2) For accurate data, its digital characteristics are determined according to the cloud model rules; among them, the rock formation attitude index, fault fracture zone width index, tunnel length index, tunnel excavation span index, one-time excavation advance index and tunnel burial depth index are quantitative indicators, that is, accurate data, and accurate observation values can be obtained from the construction site.

[0046] ExpectedEx: Usually we can directly calculate the average value of the data as the expectation. For example, for a set of data points x1, x2, ..., xn, the expectation is Here, n is the total number of data points.

[0047] Entropy En: can be estimated approximately by calculating the standard deviation of the data. A common method is to first calculate the variance of the data. Then the entropy En can be approximately expressed as a function related to the variance, such as E n =kσ 2; where k is an appropriate constant that needs to be adjusted according to specific circumstances.

[0048] Super entropy He: We can observe how the discreteness of data changes with different conditions, or we can fit the data by building a more complex statistical model to obtain an estimated value of super entropy.

[0049] (3) For uncertain data, gray system theory is used to express them as gray numbers. Among them, the surrounding rock grade index, lithologic characteristic index, advanced geological prediction index, monitoring and measurement index, support effect index, on-site safety system index, engineering data integrity index, risk management and control capability index, surrounding residents' response index, and project funding status index are qualitative indicators, that is, uncertain data. Accurate observation values cannot be obtained from the construction site.

[0050] Gray numbers refer to numbers with incomplete information, reflecting the uncertainty and ambiguity of things. For example, the evaluation of management factor indicators may not be given an exact value due to insufficient information, and instead be expressed as a range or a number with some ambiguity.

[0051] For uncertain data such as qualitative indicators, expert evaluation method, fuzzy statistics method and historical data analysis method can be used to divide the risk level and determine its gray number.

[0052] Expert Evaluation Method: An evaluation team consisting of tunnel engineering experts, safety management experts, and personnel with extensive tunnel construction experience will assess on-site safety system indicators based on their professional knowledge and practical experience, such as system integrity, strictness of implementation, and effectiveness of training. Based on the opinions of the experts, a gray number range is determined. For example, if, after discussion and analysis, the experts determine that the integrity of on-site safety system indicators is between good and fair, this gray number can be expressed as [0.6, 0.8], where 0 indicates complete non-implementation and 1 indicates strict implementation.

[0053] Fuzzy statistics: Collect a large amount of real-world data and case studies related to tunnel construction safety regulations, including those from this and similar tunnel projects. Organize and analyze this data to determine the risk level and value range of on-site safety regulations indicators. Using fuzzy statistics, classify the data into three fuzzy categories. For example, the integrity of on-site safety regulations can be categorized as "high," "medium," and "low." Different fuzzy categories correspond to different risk levels, and the corresponding gray number range is determined for each category. Assume that statistical analysis reveals that the integrity of on-site safety regulations indicators falls into the "medium" category, with a corresponding gray number range of [0.6, 0.8].

[0054] Historical Data Analysis: This method searches for safety system data from previous similar projects within the tunnel construction unit, as well as historical data from other similar tunnel projects within the industry. This data is then analyzed to assess the implementation of on-site safety system indicators, any existing issues, and their impact on construction safety. Based on the statistical analysis of this historical data and the specific circumstances of the current tunnel construction, the hazard level and gray number range of the on-site safety system indicators are determined. For example, if the on-site safety system in similar projects was well implemented, the gray number range for the relevant indicators would be between [0.8, 1]. However, if the on-site safety system of the current project has some room for improvement but a good foundation, the gray number range could be set to [0.6, 0.8].

[0055] Traditional grey models only address the incompleteness of grey information, and the grey number's preference for a particular whitening value is often a random number within a certain range. Cloud models, on the other hand, reflect and integrate the fuzziness and randomness of uncertainty, creating a mapping between qualitative and quantitative factors. To overcome these limitations, a grey-cloud model is developed based on the cloud and grey models, improving the whitening weight function in the traditional grey model.

[0056] In the ash cloud model, the horizontal axis is the value range of the ash number, and the left and right limit values [Lx, Rx], expectation Ex, entropy En and excess entropy He are the digital characteristics of the ash cloud.

[0057] The calculation formula for each digital feature is:

[0058]

[0059] Where: b n is a given constant, generally ranging from 6 to 8.

[0060] (4) Classification of the danger levels of each secondary indicator

[0061] Data risk classification can be determined based on expectation and entropy: Expectation (Ex) represents the central tendency of the secondary indicator, and entropy (En) reflects the uncertainty range of the secondary indicator. The boundaries of each level can be determined based on expectation and entropy. Each secondary indicator is divided into four interval levels: low risk (C1), medium risk (C2), high risk (C3), and extremely high risk (C4).

[0062] For example, if the cloud model expectation Ex of the tunnel length is 3000 and the entropy En is 2000, it can be considered that the range of the two entropies on the left and right, centered on the expectation, is the risk level, that is, 0-1000 is low risk; 1000-3000 is medium risk, 3000-5000 is high risk, and greater than 5000 is extremely high risk.

[0063] The four risk classifications for uncertain data are divided according to the gray number range in step (3).

[0064] The classification of danger levels can provide a preliminary assessment of the risk profile of various tunnel construction situations. Each secondary indicator is divided into four levels: low risk (C1), medium risk (C2), high risk (C3), and extremely high risk (C4).

[0065] The classification of all indicators is shown in Table 1:

[0066] Table 1 Classification of Tunnel Construction Safety Assessment Indicators

[0067]

[0068] According to the above steps, the tunnel construction safety assessment index grading table is updated, and the grading calculation of qualitative indicators is converted into quantitative grading. The evaluation index system for tunnel construction safety assessment is shown in Table 2.

[0069] Table 2 Evaluation index system for tunnel construction safety assessment

[0070]

[0071]

[0072] In an exemplary embodiment, the gray number range of each secondary indicator is determined according to the danger level of each secondary indicator in step 202, specifically steps 301 to 302:

[0073] Step 301 : Based on the data of each qualitative indicator, an expert evaluation method is used to evaluate the risk level of each qualitative indicator to determine the risk level of each qualitative indicator.

[0074] Specifically, the expert evaluation method introduced above is used to evaluate the risk level of each qualitative indicator. Alternatively, any one of the fuzzy statistics method and the historical data analysis method can be used to evaluate the risk level of each qualitative indicator to determine the risk level of each qualitative indicator.

[0075] Step 302 : normalize the data of each quantitative indicator, and determine the risk level of each quantitative indicator based on the normalized data of each quantitative indicator.

[0076] In an exemplary embodiment, step 204 specifically includes steps 401 and 402:

[0077] Step 401: According to the gray number range, the gray correlation analysis method is used to obtain the correlation coefficient of each secondary index.

[0078] Grey relational analysis formula: Let the reference sequence X0 = {x0(k)|k = 1, 2, ..., n}, the comparison sequence X i ={x i(k)|k=1,2,…,n}, correlation coefficient

[0079] Among them, ρ is the resolution coefficient, usually 0.5; max i max k |x0(k)-x i (k)| is the maximum value among all absolute differences, min i min k |x0(k)-x i (k)| is the minimum of all absolute differences.

[0080] Step 402 : Based on the correlation coefficient of each secondary indicator, a correlation calculation formula is used to calculate the correlation between each primary indicator and the tunnel construction safety status.

[0081] The formula for calculating the correlation is:

[0082]

[0083] Among them, γ i is the correlation between the i-th first-level indicator and different safety states of tunnel construction, ξ i (k) is the correlation coefficient of the kth secondary indicator in the i-th primary indicator, and n is the total number of secondary indicators.

[0084] For example, suppose the assessment results in the on-site safety system index R of the management factor 31 , Engineering data completeness index R 32 , Risk control capability index R 33 , Surrounding residents' reaction index R 34 , Project funding status indicator R 35 The risk levels are C2, C2, C1, C3, and C1, and the corresponding gray number ranges are [0.5~0.8), [0.5~0.7), [0.8~1), [0.8~1), and [0.4~0.6]; According to the formula The calculation can get the on-site safety system R 31 , project data completeness R 32 , Risk management capabilities 33 , the reaction rate of surrounding residents R 34 、Project funding situation 35 E x The correlation coefficients are 0.65, 0.6, 0.9, 0.9, and 0.5 respectively; assuming the reference sequence is 0.6, 0.6, 0.6, 0.6, and 0.6, the correlation coefficients are 0.75, 1, 0.33, 0.33, and 0.6 respectively according to the correlation coefficient formula. The correlation between management factor indicators and tunnel construction safety status is 0.602.

[0085] For the first-level indicators of geological factors and construction factors, the data are normalized and the gray number range is calculated through the correlation coefficient formula to obtain the corresponding correlation degree.

[0086] Assume that the surrounding rock grade index R obtained by evaluating the geological factor index 11 , lithologic characteristic index R 12 , rock formation occurrence index R 13 , Fault fracture zone width index R 14 The risk levels are C2, C2, C3, C2, and the surrounding rock grade index R 11 , lithologic characteristic index R 12 The corresponding gray numbers are [0.4~0.6) and [0.6~0.8). It can be seen from the formula Get E x is 0.5, 0.7, and the rock formation index R 13 C3, fault fracture zone width index R 14 After the C2 level of the accurate data is normalized, the gray number range is [0.5-0.8), [0.8-0.9). According to the specific measured data, it is assumed that the normalized values corresponding to the data are 0.6 and 0.85, so the comparison sequence is 0.5, 0.7, 0.6, and 0.85; assuming that the reference sequence is 0.6, 0.6, 0.7, and 0.8, the correlation coefficient formula can be obtained as 0.67, 0.67, 0.67, and 1 respectively. According to the correlation formula The correlation between geological factor indicators and tunnel construction safety status is 0.7525.

[0087] Assume that the tunnel length index R obtained by evaluating the construction factor index 21 , Tunnel excavation span index R 22 , one-time excavation footage index R 23 , advanced geological prediction index R 24 , monitoring measurement indicators R 25 , support effect index R 26 , tunnel depth index R 27 The risk levels are C1, C2, C2, C1, C2, C2, C1, and the advanced geological prediction index R 24 , monitoring measurement indicators R 25 , support effect index R 26 The corresponding gray number range is [0.7~1), [0.5~0.8), [0.6~0.8), according to the formula Get E x 0.85, 0.65, 0.7; tunnel length index R 21 , Tunnel excavation span index R 22, one-time excavation footage index R 23 , tunnel depth index R 27 After normalization of the corresponding levels of accurate data, the gray number range is [0.9-1), [0.7-0.8), [0.8-0.9), [0.9-1]. Based on the specific measured data, assuming that the corresponding normalized values are 0.9, 0.7, 0.8, and 0.9; the comparison sequence is 0.9, 0.7, 0.8, 0.85, 0.65, 0.7, and 0.9; assuming the reference sequence is 0.8, 0.8, 0.7, 0.8, 0.7, 0.8, and 0.8. Using the correlation coefficient formula, the correlation coefficients are 0.67, 0.67, 0.67, 1, 1, 0.67, and 0.67, respectively.

[0088] According to the correlation formula The correlation between the construction factor index and the tunnel construction safety status is 0.76.

[0089] Therefore, it is concluded that the correlation between the geological factor index, construction factor index, and management factor index in the first-level index is 0.7525, 0.76, and 0.602 respectively.

[0090] In an exemplary embodiment, step 205 specifically includes steps 501 to 505:

[0091] Step 501: Determine the weight of each first-level indicator according to the correlation degree, and use the weight as the probability that each first-level indicator will affect the tunnel construction in different safety states.

[0092] For example, the correlations among the first-level indicators for geological factors, construction factors, and management factors are 0.7525, 0.76, and 0.602, respectively. The weights of each first-level indicator are determined based on these correlations. Therefore, the weights of geological factors, construction factors, and management factors are 28.47%, 35.68%, and 35.95%, respectively. Next, the Bayesian algorithm is used to calculate the impact of these three first-level indicators on tunnel construction safety.

[0093] Step 502: Determine the prior probability of the Bayesian algorithm; wherein the prior probability is the probability that the tunnel construction is in different safety states when the influence of each primary indicator is not considered during the tunnel construction.

[0094] Let A represent the safety status of tunnel construction, with A taking three possible values: A1 (safe), A2 (average), and A3 (dangerous). Let B1 represent the geological factor index, B2 the construction factor index, and B3 the management factor index. Their probabilities are P(B1) = 0.2847, P(B2) = 0.3568, and P(B3) = 0.3595.

[0095] Determine the prior probability P(Ai), where Ai represents the safety state of the i-th tunnel construction. This represents the probability of the tunnel construction being in different safety states, ignoring the influence of the primary indicators. This can be determined based on statistical data from previous similar tunnel projects. For example, P(A1) = 0.6, P(A2) = 0.3, and P(A3) = 0.1.

[0096] Step 503 , calculating each conditional probability based on the prior probability and the probability of each first-level indicator affecting the tunnel construction in different safety states; wherein the conditional probability is the probability of the tunnel construction in different safety states under the influence of each first-level indicator.

[0097] Determine the conditional probability (i.e., likelihood) P(Bj|Ai), where j takes the values of 1, 2, and 3, representing the probability of the tunnel construction being in different safety states Ai under the influence of each primary indicator Bj. In the specific implementation process, the conditional probability also needs to be determined based on actual engineering experience, historical data, or expert judgment. For example:

[0098] When Ai = A1 (safe): P(B1|A1) = 0.7, P(B2|A1) = 0.6, P(B3|A1) = 0.6;

[0099] When Ai = A2 (general): P(B1|A2) = 0.4, P(B2|A2) = 0.3, P(B3|A2) = 0.3;

[0100] When Ai=A3 (dangerous): P(B1|A3)=0.1, P(B2|A3)=0.1, P(B3|A3)=0.1.

[0101] Step 504 : Calculate the posterior probability of the tunnel construction being in different safety states based on the conditional probabilities.

[0102] Combine the conditional probabilities obtained in step 503 to calculate the joint probability P(B1, B2, B3|Ai):

[0103] Since the geological factor index, construction factor index, and management factor index are independent of each other, when i=1 (A=A1):

[0104] P(B1, B2, B3∣A1)=P(B1∣A1)P(B2∣A1)P(B3∣A1)=0.7×0.6×0.6=0.252;

[0105] When i=2(A=A2):

[0106] P(B1, B2, B3∣A2)=P(B1∣A2)P(B2∣A2)P(B3∣A2)=0.4×0.3×0.3=0.036;

[0107] When i=3 (A=A3):

[0108] P(B1, B2, B3∣A3)=P(B1∣A3)P(B2∣A3)P(B3∣A3)=0.1×0.1×0.1=0.001.

[0109] According to the total probability formula: Calculate P(B1, B2, B3):

[0110] P(B1,B2,B3)=P(B1,B2,B3∣A1)P(A1)+P(B1,B2,B3∣A2)P(A2)+P(B1,B2,B3∣A3)P(A3);

[0111] Then P(B1, B2, B3) = 0.252 × 0.6 + 0.036 × 0.3 + 0.001 × 0.1;

[0112] P(B1, B2, B3)=0.1512+0.0108+0.0001=0.1621.

[0113] Step 505 : Determine a tunnel construction safety assessment result based on the posterior probabilities of the tunnel construction being in different safety states. This includes comparing the posterior probabilities of the tunnel construction being in different safety states and taking the tunnel construction safety state with the maximum posterior probability as the tunnel construction safety assessment result.

[0114] Specifically, according to the result calculated in step 504, the posterior probability P(Ai|B1, B2, B3) is calculated:

[0115] When i=1:

[0116] P(A1∣B1,B2,B3)=P(B1,B2,B3,∣A1)P(A1) / P(B1,B2,B3)

[0117] P(A1|B1,B2,B3)=0.252×0.6÷0.1621≈0.933;

[0118] When i=2:

[0119] P(A2|B1,B2,B3)=P(B1,B2,B3,|A2)P(A2) / P(B1,B2,B3)

[0120] P(A2∣B1, B2, B3)=0.036×0.3÷0.1621≈0.067;

[0121] When i=3:

[0122] P(A3∣B1,B2,B3)=P(B1,B2,B3∣A3)P(A3) / P(B1,B2,B3)

[0123] P(A3∣B1, B2, B3)=0.001×0.1÷0.1621≈0.001.

[0124] Comparing P(A1|B1, B2, B3) ≈ 0.93, P(A2|B1, B2, B3) ≈ 0.067, and P(A3|B1, B2, B3) ≈ 0.001, we conclude that P(A1|B1, B2, B3) is the largest value, and therefore, the Bayesian algorithm indicates that the tunnel is safe.

[0125] This application has the following beneficial effects:

[0126] (1) The Bayesian algorithm is innovatively combined with the ash cloud model for tunnel construction safety assessment, and the advantages of both are used to comprehensively handle the uncertainty information and multi-source data in construction.

[0127] (2) Construct an evaluation index system for tunnel construction safety assessment, covering multi-dimensional factors in multiple aspects, and provide a rich and accurate data basis for combining algorithms.

[0128] (3) The weight of each indicator is determined based on grey correlation analysis, and applied to the Bayesian algorithm conditional probability determination and grey cloud model construction to improve the accuracy and reliability of the evaluation.

[0129] (4) The method in this application can adapt to safety, danger or comprehensive assessment involving various factors, has strong adaptability, and the calculation results are more comprehensive and accurate.

[0130] Based on the same inventive concept, embodiments of the present application also provide a Bayesian ash cloud model-based tunnel construction safety assessment device for implementing the aforementioned Bayesian ash cloud model-based tunnel construction safety assessment method. The solution provided by this device is similar to the solution described in the aforementioned method. Therefore, the specific limitations of one or more embodiments of the Bayesian ash cloud model-based tunnel construction safety assessment device provided below can be found in the above-mentioned limitations of the Bayesian ash cloud model-based tunnel construction safety assessment method, and will not be repeated here.

[0131] In an exemplary embodiment, Figure 5 As shown, a tunnel construction safety assessment device based on a Bayesian ash cloud model is provided, comprising:

[0132] The first construction module 51 is used to construct an evaluation index system for tunnel construction safety evaluation; the evaluation index system includes a plurality of first-level indicators, and each first-level indicator includes a plurality of second-level indicators.

[0133] The danger level determination module 52 is used to collect data of each secondary indicator during the tunnel construction process in the current period, and determine the danger level of each secondary indicator based on the data of each secondary indicator.

[0134] The gray number range determination module 53 is used to determine the gray number range of each secondary indicator according to the danger level of each secondary indicator.

[0135] The correlation calculation module 54 is used to calculate the correlation between each primary indicator and the different safety states of the tunnel construction based on the gray number range using the gray cloud model; the safety states include safe, general and dangerous.

[0136] The evaluation module 55 is used to evaluate the tunnel construction safety based on the correlation degree using the Bayesian algorithm to obtain the tunnel construction safety evaluation result for the current period.

[0137] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Figure 6 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O) and a communication interface. The processor, memory and input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used for data of various secondary indicators during the tunnel construction process. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a tunnel construction safety assessment method based on the Bayesian ash cloud model is implemented.

[0138] Those skilled in the art will understand that Figure 6 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0139] In an exemplary embodiment, a computer device is further provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps in the above method embodiments when executing the computer program.

[0140] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0141] In an exemplary embodiment, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0142] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0143] Those skilled in the art will understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0144] The databases involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processors involved in the various embodiments provided herein may include, but are not limited to, general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic units, data processing logic units based on quantum computing, and the like.

[0145] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0146] This document uses specific examples to illustrate the principles and implementation methods of this application. The description of the above examples is only intended to help understand the method and core concept of this application. At the same time, for those skilled in the art, based on the concept of this application, there may be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A tunnel construction safety assessment method based on a Bayesian ash cloud model, characterized in that: include: Constructing an evaluation index system for tunnel construction safety assessment; the evaluation index system includes multiple first-level indicators, each of which includes multiple second-level indicators; Collect data on each secondary indicator during the current tunnel construction process, and determine the danger level of each secondary indicator based on the data; Determine the gray number range of each secondary indicator according to the danger level of each secondary indicator; According to the range of gray numbers, the gray cloud model is used to calculate the correlation between each first-level index and the different safety states of tunnel construction; Safety status includes safe, normal and dangerous; Based on the correlation degree, the Bayesian algorithm is used to evaluate the tunnel construction safety and obtain the evaluation results of the tunnel construction safety in the current period.

2. The tunnel construction safety assessment method based on the Bayesian ash cloud model according to claim 1 is characterized in that: The first-level indicators include geological factor indicators, construction factor indicators and management factor indicators; the second-level indicators among the geological factor indicators include surrounding rock grade indicators, lithologic characteristic indicators, surrounding rock grade indicators and lithologic characteristic indicators; the second-level indicators among the construction factor indicators include tunnel length indicators, tunnel excavation span indicators, one-time excavation progress indicators, advanced geological prediction indicators, monitoring and measurement indicators, support effect indicators and tunnel burial depth indicators; the second-level indicators among the management factor indicators include on-site safety system indicators, engineering data completeness indicators, risk management and control capability indicators, surrounding residents' response indicators and project funding status indicators.

3. The tunnel construction safety assessment method based on the Bayesian ash cloud model according to claim 2 is characterized in that: Quantitative indicators include rock formation occurrence index, fault fracture zone width index, tunnel length index, tunnel excavation span index, single excavation footage index, and tunnel burial depth index. Qualitative indicators include surrounding rock grade index, lithologic characteristic index, advanced geological prediction index, monitoring and measurement index, support effectiveness index, on-site safety system index, engineering data integrity index, risk management and control capability index, surrounding residents' response index, and project funding status index. The hazard level of each secondary indicator is determined based on the data of each secondary indicator, including: Based on the data of each qualitative indicator, the expert evaluation method is used to evaluate the risk level of each qualitative indicator and determine the risk level of each qualitative indicator; The data of each quantitative indicator is normalized, and the risk level of each quantitative indicator is determined based on the normalized data of each quantitative indicator.

4. The tunnel construction safety assessment method based on the Bayesian ash cloud model according to claim 1 is characterized in that: Based on the gray number range, the gray cloud model is used to calculate the correlation between each primary indicator and the different safety states of tunnel construction, including: According to the range of gray numbers, the gray correlation analysis method is used to obtain the correlation coefficient of each secondary index; Based on the correlation coefficient of each secondary indicator, the correlation calculation formula is used to calculate the correlation between each primary indicator and the tunnel construction safety status; The correlation calculation formula is: Among them, γ i is the correlation between the i-th first-level indicator and different safety states of tunnel construction, ξ i (k) is the correlation coefficient of the kth secondary indicator in the i-th primary indicator, and n is the total number of secondary indicators.

5. The tunnel construction safety assessment method based on the Bayesian ash cloud model according to claim 1 is characterized in that: Based on the correlation, the Bayesian algorithm is used to evaluate the tunnel construction safety, and the tunnel construction safety assessment results are obtained, including: Determine the weight of each first-level indicator based on the degree of correlation, and use the weight as the probability of each first-level indicator affecting the tunnel construction in different safety states; Determining a priori probability of the Bayesian algorithm; wherein the priori probability is the probability of the tunnel construction being in different safety states when the influence of each primary indicator is not considered during the tunnel construction; Calculating conditional probabilities based on the prior probability and the probability of each first-level indicator affecting the tunnel construction in different safety states; wherein the conditional probabilities are the probabilities of the tunnel construction in different safety states under the influence of each first-level indicator; Calculate the posterior probability of tunnel construction being in different safety states based on various conditional probabilities; The tunnel construction safety assessment results are determined based on the posterior probability that the tunnel construction is in different safety states.

6. The method for evaluating tunnel construction safety based on the Bayesian ash cloud model according to claim 5, characterized in that: The assessment results of tunnel construction safety are determined based on the posterior probabilities of the tunnel construction being in different safety states, including: Compare the posterior probabilities of tunnel construction being in different safety states; The tunnel construction safety status with the maximum posterior probability is taken as the tunnel construction safety assessment result.

7. A tunnel construction safety assessment device based on a Bayesian ash cloud model, characterized in that: include: A first building module is used to construct an evaluation index system for tunnel construction safety assessment; the evaluation index system includes multiple first-level indicators, and each first-level indicator includes multiple second-level indicators; A hazard level determination module is used to collect data on various secondary indicators during the tunnel construction process during the current period and determine the hazard level of each secondary indicator based on the data of each secondary indicator; A gray number range determination module is used to determine the gray number range of each secondary indicator according to the danger level of each secondary indicator; The correlation calculation module is used to calculate the correlation between each primary indicator and the different safety states of tunnel construction based on the gray number range and the gray cloud model; Safety status includes safe, normal and dangerous; The evaluation module is used to evaluate the tunnel construction safety based on the correlation degree and adopt the Bayesian algorithm to obtain the tunnel construction safety evaluation results for the current period.

8. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the tunnel construction safety assessment method based on the Bayesian ash cloud model according to any one of claims 1 to 6.

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 tunnel construction safety assessment method based on the Bayesian ash cloud model described in any one of claims 1 to 6 is implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the tunnel construction safety assessment method based on the Bayesian ash cloud model described in any one of claims 1 to 6 is implemented.

Images