CN118822284A - Tunnel operation safety assessment method and system based on multi-source risk factors - Google Patents

Abstract

The present application relates to the technical field of tunnel operation, and specifically discloses a tunnel operation safety assessment method and system based on multi-source risk factors. The method comprises obtaining multi-source information data that affects the health status of the tunnel during operation, comprehensively evaluating the importance of indicators of the multi-source information data based on multiple methods, determining the importance of various types of information, performing a difference elimination analysis on the importance, obtaining multi-source comprehensive evaluation weights of corresponding risk factors, sorting the multi-source comprehensive evaluation weights and determining the core risk factors of the tunnel in combination with the complexity required on site, building a corresponding quantitative assessment model according to the type of core risk factors, outputting the indicator health score of each core risk factor based on the quantitative assessment model, inputting each indicator health score and the corresponding comprehensive evaluation weight into the scoring model to obtain the tunnel operation safety health status assessment result, and realizing the multi-source fusion assessment of the health status of the tunnel during operation.

Description

Tunnel operation safety assessment method and system based on multi-source risk factors

Technical Field

The present application relates to the field of tunnel operation technology, and in particular to a tunnel operation safety assessment method and system based on multi-source risk factors.

Background Art

With the rapid development of infrastructure construction in my country, tunnel projects, as an important part of the transportation system, are increasing in number and scale. However, the safety issues faced by tunnels during operation are becoming increasingly complex. The variability of geological conditions, differences in construction quality, and uncertainty in operation and management may threaten the safety of tunnel structures. In recent years, scholars at home and abroad have conducted extensive research on tunnel safety evaluation methods and proposed a variety of comprehensive methods based on geological surveys, structural monitoring, and risk assessment. Traditional tunnel safety evaluation methods mainly rely on a single information source and are difficult to fully reflect the actual status of the tunnel. For example, some studies only focus on the impact of geological conditions on tunnel safety, while ignoring other important factors such as construction quality and operation management. In addition, existing evaluation methods often lack the comprehensive use of real-time monitoring data, making it difficult to timely discover and warn potential safety issues. The development of multi-source information fusion technology provides new ideas for tunnel safety evaluation.

In related technologies, by integrating automated monitoring data, manual inspection data, and expert evaluation information, the health status of the tunnel can be evaluated more comprehensively and accurately. For example, in an undersea tunnel health monitoring system based on multi-source information fusion, tunnel risk assessment is achieved through comprehensive analysis of tunnel structure deformation, stress strain, and environmental parameters. However, it is mainly applicable to the analysis of undersea tunnels, and the amount of data is huge, which requires high capabilities of data analysts and is difficult to be extended to general projects. Fuzzy comprehensive evaluation methods have been widely used in engineering safety evaluation that is difficult to accurately describe because they can handle uncertainty and fuzzy information.

However, current research focuses on a single evaluation method, lacking the comprehensive application of multi-source information and a systematic risk assessment model. In particular, there are still some deficiencies in the health assessment of tunnels during operation: for example, most studies focus on risk management during the tunnel construction period, while ignoring long-term health monitoring and risk assessment during the tunnel operation period. Secondly, the existing health assessment model has limitations in the comprehensive use of multi-source information and dynamic risk assessment, making it difficult to cope with complex and changing operating environments and emergencies.

Summary of the invention

The present application aims to solve the problems in the prior art that long-term health monitoring and risk assessment during the tunnel operation period are neglected, there is a lack of a safe, automated and accurate assessment method for the tunnel's operating status, and it fails to combine the comprehensive utilization of multi-source information and dynamic risk assessment. Therefore, a tunnel operation safety assessment method and system based on multi-source risk factors is proposed.

In order to achieve the above objectives, in a first aspect, the present application provides a tunnel operation safety assessment method based on multi-source risk factors, comprising:

Obtain multi-source information data that affects the health status of the tunnel during operation;

Comprehensively evaluate the importance of indicators of the multi-source information data based on multiple methods to determine the importance of each type of information, wherein the multiple methods include evaluation by domain experts;

Performing a difference elimination analysis on the importance levels to obtain multi-source comprehensive evaluation weights of corresponding risk factors;

Sorting the multi-source comprehensive evaluation weights and determining the core risk factors of the tunnel in combination with the complexity of site requirements;

Building a corresponding quantitative assessment model according to the core risk factor type, and outputting the indicator health score of each core risk factor based on the quantitative assessment model;

A health scoring model for the tunnel operation period is established, and the health score of each indicator and the corresponding multi-source comprehensive evaluation weight are input into the scoring model to obtain the assessment results of the safe and healthy status of tunnel operation.

In some possible implementations, the importance of indicators of the multi-source information data is comprehensively evaluated based on a variety of methods to determine the importance of each type of information, and the various methods include evaluation by domain experts, including:

The confidence of the expert evaluation in the field is evaluated based on the expert confidence index, wherein the expert confidence index calculation formula is:

In the formula, is the evaluation ability index of the mth expert, is the subjective reliability index of the mth expert;

Determining the relative importance of the domain expert's evaluation of the risk factor based on the confidence level of the domain expert's evaluation;

The degree of importance of each type of information is determined based on domain expert evaluation of different relative importance.

In some possible implementations, the domain expert evaluation based on different relative importance determines the importance of each type of information, including:

Construct a fuzzy number corresponding to the relative importance of domain experts, and assign the weights of experts based on the fuzzy number, where:

The fuzzy number expression is:

The weight expression is:

In the formula, represents the important membership degree evaluated by the kth expert, Indicates that the k-th expert has an unimportant membership, It represents the hesitation between the kth expert's evaluation of importance and unimportance.

In some possible implementations, the determining the importance of each type of information based on the evaluation of domain experts of different relative importances further includes:

Based on the evaluation results provided by each expert, an importance evaluation matrix is constructed to compare the different influencing factors of the target.

The importance evaluation matrix expression is:

In the formula, is the importance evaluation matrix, Factors that affect tunnel health: It is the fuzzy evaluation number determined by the k-th domain expert for the i-th influencing factor at the j-th level.

In some possible implementations, the performing of the difference elimination analysis on the importance levels to obtain the multi-source comprehensive evaluation weights of the corresponding risk factors includes:

Constructing a summary group decision matrix based on the evaluation information of domain experts and determining the weights of risk factors;

constructing a weighted summary group decision matrix based on the weights of the risk factors and the summary group decision matrix;

Determining a positive ideal solution and a negative ideal solution according to the weighted summary group decision matrix;

According to the positive ideal solution and the negative ideal solution, the distance between the risk factor and the positive ideal solution and the negative ideal solution is determined to obtain the multi-source comprehensive evaluation weight, wherein the multi-source comprehensive evaluation weight includes a relative proximity index value of the risk factor.

In some possible implementations, determining the distance between the risk factor and the positive ideal solution and the negative ideal solution according to the positive ideal solution and the negative ideal solution to obtain the multi-source comprehensive evaluation weight includes:

Based on the formula determining a first distance between the risk factor and the positive ideal solution;

Based on the formula determining a second distance between the risk factor and the negative ideal solution;

In the formula, is the first distance, is the second distance, n is the number of importance levels, and are the membership and non-membership of the positive ideal solution, respectively. and are the membership and non-membership of the negative ideal solution, respectively. is the hesitation degree of the positive ideal solution, is the hesitation degree of the negative ideal solution, It represents the weighted evaluation importance of the i-th influencing factor at the j-th level. Indicates the membership degree of the i-th influencing factor at the j-th level that the weighted evaluation is not important, It represents the hesitation degree of importance or unimportance of the i-th influencing factor at the j-th level.

In some possible implementations, the tunnel operation health scoring model is constructed, and each of the health scores of the indicators and the corresponding comprehensive evaluation weights are input into the scoring model to obtain the tunnel operation safety and health status assessment results, including:

The tunnel operation health scoring model is constructed based on the factor weight weighted average method;

Based on the tunnel operation period health scoring model, the comprehensive evaluation weight is normalized and combined with the indicator health score to obtain the final health score J, where:

The final health score J is expressed as:

In the formula, represents the comprehensive evaluation weight of the i-th normalized key factor, It represents the indicator health score of the i-th key factor, and n represents the total number of selected key factors.

Compared with the prior art, the above technical solutions in the embodiments of the present application have at least the following technical effects or advantages:

1) The method is implemented by creating multiple models, and the importance of indicators of multi-source information data is comprehensively evaluated through multiple methods. The importance evaluation method of different factors is defined, and further a multi-source fusion weight calculation method and model that can correct and unify the importance evaluation of factors affecting different sources and evaluation standards is provided. The evaluation differences of the same evaluation indicators from different sources are corrected, and the fusion calculation weights of each factor are derived, making it possible to simplify and focus on a large number of factors, greatly improving the analysis efficiency. At the same time, a method and calculation model for quantitative evaluation of different factors are provided, so that different types of influencing factors can be better quantitatively analyzed, and a method and model for integrating key factors of quantitative evaluation and tunnel health fusion scoring are provided, realizing multi-source fusion evaluation and scoring of the health status of tunnels during operation.

2) Through the identification of risk factors and automated health risk assessment methods based on multi-source information fusion during the operation period of the tunnel, the health status of the tunnel operation status can be automatically scored based on multi-source information fusion, thereby improving the response speed of tunnel safety assessment, saving the labor costs of traditional maintenance and safety assessment, improving the efficiency of civil engineering construction, and facilitating operation and maintenance.

In a second aspect, the present application provides a tunnel operation safety assessment system based on multi-source risk factors, comprising:

An acquisition module is configured to acquire multi-source information data that affects the health status of the tunnel during operation, wherein the multi-source information data includes geological conditions, human factors, and random factors;

A first determination module is configured to perform a single analysis on the multi-source information data based on a plurality of methods to determine the importance of each type of information, wherein the plurality of methods include domain expert evaluation;

A first data processing module is configured to perform a difference elimination analysis on the importance degree to obtain a multi-source comprehensive evaluation weight of the corresponding risk factor, which includes constructing a summary group decision matrix based on the evaluation information of domain experts and determining the weight of the risk factor, constructing a weighted summary group decision matrix based on the weight of the risk factor and the summary group decision matrix, determining a positive ideal solution and a negative ideal solution according to the weighted summary group decision matrix, determining the distance between the risk factor and the positive ideal solution and the negative ideal solution according to the positive ideal solution and the negative ideal solution, and obtaining the multi-source comprehensive evaluation weight;

A second determination module is configured to sort the multi-source comprehensive evaluation weights and determine the core risk factor of the tunnel in combination with the complexity of the site requirements;

The second data processing module is configured to build a corresponding quantitative assessment model according to the core risk factor type, and output the indicator health score of each core risk factor based on the quantitative assessment model, wherein the quantitative assessment model includes quantitative scoring of changes in vibration response, tunnel settlement and convergence, wherein:

The quantitative scoring formula for tunnel vibration response is:

The quantitative scoring formula for tunnel settlement changes is:

The quantitative scoring formula for tunnel convergence change is:

In the formula, is the current tunnel vibration amplitude change rate, is the initial vibration amplitude change rate, is the current daily settlement rate of the tunnel, is the initial settlement rate of the tunnel; and is the warning factor, is the maximum daily convergence rate of the tunnel, is the initial convergence rate of the tunnel;

The third data processing module is configured to build a health scoring model for the tunnel operation period, and input the health score of each indicator and the corresponding multi-source comprehensive evaluation weight into the scoring model to obtain the tunnel operation safety and health status assessment result.

In a third aspect, the present application further provides an electronic device, including:

at least one processor; and

a memory communicatively connected to the at least one processor; wherein,

The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the steps of the tunnel operation safety assessment method based on multi-source risk factors provided in any one of the first aspects above.

In a fourth aspect, the present application also provides a computer-readable storage medium having computer program instructions stored thereon, which, when executed by a processor, implement the steps of the tunnel operation safety assessment method based on multi-source risk factors provided in any one of the first aspects above.

It can be understood that the beneficial effects of the technical solutions provided in the second, third and fourth aspects can be found in the relevant description of the first aspect, and will not be repeated here.

Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application.

BRIEF DESCRIPTION OF THE DRAWINGS

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. 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.

FIG1 is a flow chart of a tunnel operation safety assessment method based on multi-source risk factors according to an embodiment of the present application;

FIG2 is a sub-flow chart of step S300 of the tunnel operation safety assessment method based on multi-source risk factors according to an embodiment of the present application;

FIG3 is a block diagram of factors affecting tunnel operation safety according to an embodiment of the present application;

FIG4 is a radar chart of impact factor indicators according to an embodiment of the present application;

FIG5 is a block diagram of a tunnel operation safety assessment system based on multi-source risk factors according to an embodiment of the present application;

DETAILED DESCRIPTION

The embodiments of the present application are described in detail below. The embodiments described with reference to the accompanying drawings are exemplary. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

It should be noted that, unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein in the specification of this application are only for the purpose of describing specific implementations and are not intended to limit this application. The term "and/or" used herein includes any and all combinations of one or more of the related listed items.

Referring to FIG. 1 and FIG. 2 , this embodiment provides a tunnel lining crack detection method based on deep learning, including:

In order to achieve the above objectives, in a first aspect, the present application provides a tunnel operation safety assessment method based on multi-source risk factors, comprising:

Step S100: Acquire multi-source information data that affects the health status of the tunnel during operation;

In this step, it should be noted that the multi-source information data that affect the safety of the tunnel during operation include but are not limited to: 1) Geological conditions: The geological conditions of the tunnel include the surrounding rock grade of the tunnel and the surrounding stratigraphic structure, rock type, geological structure (such as faults, folds, cracks, etc.), groundwater level and its changes, soil properties (such as density, water content, expansibility, etc.), seismic activity frequency and intensity, etc. Combined with the current research content and the availability of the data itself, the tunnel surrounding rock grade and groundwater level status are mainly considered. 2) Human factors: The health status of the tunnel during operation is affected by a variety of human factors, including construction quality, technical level, maintenance management, operation management, traffic flow and load, human damage, and data management and analysis. These factors directly affect the structural stability and safety of the tunnel. The current evaluation model mainly considers the influence of factors such as construction quality, technical level, and traffic flow. 3) Random factors: Random factors mainly include unpredictable events such as equipment failure, traffic accidents, and natural disasters. Traffic accidents, especially collisions involving heavy vehicles, may cause direct impact and damage to the tunnel structure; natural disasters such as earthquakes, floods and landslides will cause serious damage to the tunnel structure and function.

It is understandable that the acquisition of multi-source information data may include: geological surveys and drilling can determine detailed information on the surrounding rock grade of the tunnel, the surrounding stratigraphic structure, rock type and geological structures (such as faults, folds, fissures, etc.). Long-term hydrological monitoring and groundwater simulation can determine the changes in groundwater levels. The main human factors such as construction quality and technical level can be evaluated through engineering archives and construction records. The data of maintenance management and operation management can be obtained through the operation management system, and the traffic flow and load can be obtained through the traffic monitoring system. In terms of random factors, the data of equipment failure can be obtained through equipment monitoring and maintenance records, while the data of traffic accidents, especially collisions of heavy vehicles, can be obtained through traffic management systems and accident reports. The impact of natural disasters such as earthquakes, floods and landslides needs to be evaluated in combination with historical data and disaster simulation.

Step S200: Comprehensively evaluate the importance of indicators of the multi-source information data based on multiple methods to determine the importance of each type of information, wherein the multiple methods include evaluation by domain experts;

In this step, multiple methods refer to methods that can scientifically evaluate the importance of multi-source information data in combination with local geological conditions, meteorological conditions, etc., including but not limited to: inviting experts in the field to evaluate the importance of information, analyzing the importance of various types of information by consulting relevant references, and analyzing the importance of various types of information by surveying geological data and hydrological and meteorological data.

For domain expert evaluation, we first need to evaluate the confidence of the experts, and use the expert confidence index (ECI) to evaluate the confidence of the expert evaluation. The expert confidence index is related to education and experience. For example, the judgment of an expert with more than 20 years of engineering experience is usually more reliable than that of a practicing engineer with only 2-3 years of engineering experience.

The formula for calculating the expert reliability index is:

In the formula, is the evaluation ability index of the mth expert, is the subjective reliability index of the mth expert;

The relative importance of the risk factor evaluation by domain experts is determined based on the confidence of the domain experts' evaluation, and the importance of each type of information is determined based on the domain experts' evaluation of different relative importances.

In one example, as decision makers or experts gain more work experience, their judgment ability will also improve. The expert evaluation ability index is divided into five levels, as shown in Table (1).

Table (1) is the grading table of the domain expert evaluation ability index

Expert subjective reliability is also divided into five levels, as shown in Table (2). The expert confidence index is divided into five levels to indicate the relevant importance of the interviewed experts. A higher ECI value indicates that the relevant importance of the expert is higher.

Table (2) is the subjective reliability grading table of domain experts

Specifically, it is also necessary to construct fuzzy numbers corresponding to the relative importance of domain experts and assign weights to experts based on the fuzzy numbers, where:

The fuzzy number expression is:

The weight expression is:

In the formula, represents the important membership degree evaluated by the kth expert, Indicates that the k-th expert has an unimportant membership, It represents the hesitation between the kth expert's evaluation of importance and unimportance.

Based on the evaluation results provided by each expert, an importance evaluation matrix is constructed to compare the different influencing factors of the target.

The importance evaluation matrix expression is:

In the formula, is the importance evaluation matrix, Factors that affect tunnel health: It is the fuzzy evaluation number determined by the k-th domain expert for the i-th influencing factor at the j-th level.

It should be noted that the degree of importance refers to the weight score of various information factors from the same method source under the same evaluation standard. The weight obtained by direct scoring can be a percentage weight, a decimal weight in the range of 0-1, or an A, B, C, D grade weight or a 1, 2, 3, 4 digital grade weight, etc., but it must be a weight that can be quantified or has a quantification rule. The evaluated weights are normalized to remove the errors caused by the different weight scoring forms. The final weights can describe the importance of different evaluation method sources to various types of information.

Step S300: performing a difference elimination analysis on the importance levels to obtain a multi-source comprehensive evaluation weight of the corresponding risk factors;

In this step, when the importance evaluation of each multi-source information data by experts in each field is obtained, these importance evaluations need to be further analyzed to eliminate the differences in the same evaluation indicators caused by different evaluation sources (such as different types of experts and different types of literature have different evaluation criteria for the same type of factors, which need to be further eliminated). Finally, the multi-source comprehensive evaluation weights of various types of information after eliminating the differences are obtained. It can be understood that these methods include but are not limited to: hierarchical analysis method, fuzzy comprehensive evaluation method, entropy method, fuzzy hierarchical analysis method, data envelopment analysis method, TOPSIS method, Bayesian network method, etc. In this implementation scheme, the fuzzy set improved TOPSIS method is preferably used for comprehensive evaluation.

In order to obtain the multi-source comprehensive evaluation weights and implement the method programmability and automatically calculate the output results on the electronic device, it is also necessary to process the importance of each multi-source information data evaluation in the following steps:

Step S310: constructing a summary group decision matrix based on the evaluation information of domain experts and determining the weights of risk factors;

In this step, the experts' individual expert judgment matrices are aggregated to construct an aggregated group decision matrix generated by the Pythagorean fuzzy weighted aggregation operator. The constructed aggregated group decision matrix and operation formula for standard rating are as follows:

In the formula, is the individual expert judgment matrix of the kth expert, n is the number of influencing factors, t is the number of importance levels of the indicators. In the specific test case, the importance level is divided into 5 levels, namely very important, important...very unimportant, It means that the kth is the fuzzy evaluation number determined by the expert for the i-th influencing factor at the j-th level. represents the Pythagorean fuzzy aggregate average (PFWA) operator, which combines the individual opinions of all experts into a collective opinion according to their weights. u represents the number of experts, or Indicates the importance of the uth or kth expert.

Step S320: constructing a weighted summary group decision matrix based on the weights of the risk factors and the summary group decision matrix;

In this step, the evaluation results of the experts are combined to obtain the summary weight of the evaluation items. Assume that the number of objects is 1. The corresponding integrated group decision matrix under the object is . Therefore, the weight of the criteria is defined as: , , the weighted summary group decision matrix is obtained by adding the weights of the criteria ( ) and the aggregated group decision matrix ( ) are multiplied together. The weighted summary group decision matrix and calculation formula are as follows:

In the formula, represents the weighted aggregate group decision matrix, represents matrix operations, express The corresponding position in the matrix , Represents the corresponding position in the integrated group decision matrix , , , Same reason.

Step S330: Determine a positive ideal solution and a negative ideal solution according to the weighted summary group decision matrix;

In this step, according to the weighted summary group decision matrix, it is necessary to further determine the weights of the alternatives. It should be noted that the alternatives can be understood as influencing factors. The weights of the alternatives are represented by triangular fuzzy numbers, and the weights of the alternatives are normalized under all states.

Triangular fuzzy number expression:

Normalized weight calculation formula:

In the formula, is the weight of the k-th expert, is the value evaluated by the kth expert based on the measured data in the sth state, u is the number of experts, is the number of states for each alternative, is the summary evaluation result of the ith alternative in the sth state, is the normalized summary evaluation result of the ith alternative in the sth state, is the lower bound of the triangular fuzzy number, is the most likely value of the triangular fuzzy number, is the upper bound of the triangular fuzzy number, Represents the normalization coefficient.

Furthermore, the positive ideal solution (PIS-X+) and negative ideal solution (NIS-X−) of the constructed model are determined. The positive ideal solution includes all benefit criterion values, while the negative ideal solution consists of all cost criterion values.

Ideal solution expression:

Positive ideal solution (PIS-X+) calculation formula:

Negative ideal solution (PIS-X+) calculation formula:

In the formula, is a positive ideal solution (PIS), is the negative ideal solution (NIS), is a collection of efficiency indicators. is a collection of cost indicators. and are the membership and non-membership of the ideal solution respectively, and are the membership and non-membership of the negative ideal solution, respectively. It represents the fuzzy number after comprehensive weighting, and represents the weighted evaluation result of the i-th alternative at the j-th importance level.

Step S340: According to the positive ideal solution and the negative ideal solution, the distance between the risk factor and the positive ideal solution and the negative ideal solution is determined to obtain a multi-source comprehensive evaluation weight, wherein the multi-source comprehensive evaluation weight includes a relative proximity index value of the risk factor.

In this step, the distance between the risk factor and the positive ideal solution and the negative ideal solution is determined according to the positive ideal solution and the negative ideal solution, and the multi-source comprehensive evaluation weight is obtained, including:

Based on the formula Determine the first distance between the risk factor and the positive ideal solution;

Based on the formula Determine the second distance between the risk factor and the negative ideal solution;

In the formula, is the first distance, is the second distance, n is the number of importance levels, and are the membership and non-membership of the positive ideal solution, respectively. and are the membership and non-membership of the negative ideal solution, respectively. is the hesitation degree of the positive ideal solution, is the hesitation degree of the negative ideal solution, It represents the weighted evaluation importance of the i-th influencing factor at the j-th level. Indicates the membership degree of the i-th influencing factor at the j-th level that the weighted evaluation is not important, It represents the hesitation degree of importance or unimportance of the i-th influencing factor at the j-th level.

Step S400: sorting the multi-source comprehensive evaluation weights and determining the core risk factors of the tunnel in combination with the complexity required on site;

In this step, the multi-source comprehensive evaluation weights are first used to sort the alternatives, and the modified closeness coefficient index (RCCI) of the ith alternative is specifically calculated. The optimal alternative is the one that is closest to the positive ideal solution (PIS) and farthest from the negative ideal solution (NIS).

The RCCI calculation formula is:

In the formula, is the first distance, is the second distance.

Then, the factors affecting the alternative plans are ranked according to the modified closeness coefficient index.

The ranking calculation formula is:

In the formula, is a set of alternatives sorted by RCCI value, containing alternatives in descending order, represents the RCCI value of the ith alternative. An intermediate variable or function used to calculate the RCCI value of the ith alternative.

The core risk factors of the tunnel are determined based on the sorting results and combined with the complexity of site requirements.

Step S500: Building a corresponding quantitative assessment model according to the core risk factor type, and outputting the indicator health score of each core risk factor based on the quantitative assessment model;

In this step, the corresponding quantitative assessment model is built according to the core risk factor type. It should be noted that multiple quantitative assessment models can be pre-built for backup. When the core risk factor type is determined and screened out, the corresponding pre-stored quantitative assessment model is directly called for quantitative calculation. Taking vibration response as an example, the evaluation method is: first, through one month of continuous on-site monitoring, the average daily increase rate of the vibration amplitude within one month is calculated. According to experience, ten times the increase rate is set as the warning threshold.

The vibration response score is calculated as:

in, is the current tunnel vibration amplitude change rate, is the rate of change of the initial vibration amplitude. Due to the lack of in-depth research, this evaluation method is highly empirical and requires further refinement of the scoring criteria.

Step S600: Build a tunnel operation health scoring model, input each indicator health score and the corresponding comprehensive evaluation weight into the scoring model to obtain the tunnel operation safety and health status assessment results.

In this step, the calculation model for the core risk factor score refers to a calculation model that can score various core risk factors in combination with the current state, including but not limited to: upper and lower limit scoring method, change rate amplitude scoring method, experience scoring method, etc. The upper and lower limit scoring method refers to determining the safest minimum value a and the most dangerous maximum value b that the current factor can take. According to the current value c, the calculation formula for the score r in percentage is:

Furthermore, the change rate amplitude scoring method refers to the change rate d of the current factor, the threshold value of the dangerous state change rate e, and the percentage score rv as shown in the formula:

It can be understood that the scoring model for tunnel health evaluation during operation refers to a model that combines the scores of each key factor and the relevant weights to comprehensively score and obtain the current tunnel health score. The comprehensive scoring method includes but is not limited to: weighted average method according to factor weights, direct average method, custom weight average method, hierarchical analysis method, TOPSIS method, entropy value method, etc. The scheme of this embodiment adopts the weighted average method of factor weights. The health scoring model of the tunnel operation period is built based on the weighted average method of factor weights. The comprehensive evaluation weights are normalized based on the health scoring model of the tunnel operation period and combined with the indicator health score to obtain the final health score J, where,

The final health score J is expressed as:

In the formula, represents the comprehensive evaluation weight of the i-th normalized key factor, It represents the indicator health score of the i-th key factor, and n represents the total number of selected key factors.

In the above method steps, multiple models are created to achieve a comprehensive evaluation of the importance of indicators of multi-source information data through multiple methods, and the importance evaluation method of different factors is defined. Furthermore, a multi-source fusion weight calculation method and model that can correct and unify the importance evaluation of factors affecting different sources and evaluation standards are provided, which realizes the correction of evaluation differences of the same evaluation indicators from different sources, and derives the fusion calculation weights of each factor, making it possible to simplify and focus on a large number of factors, greatly improving the analysis efficiency. At the same time, a method and calculation model for quantitative evaluation of different factors are provided, so that different types of influencing factors can be better quantitatively analyzed, and a method and model for integrating key factors of quantitative evaluation and tunnel health fusion scoring are provided, realizing multi-source fusion evaluation and scoring of the health status of the tunnel during operation.

In addition, through the multi-source information fusion risk factor identification and health risk automatic evaluation method of the tunnel during operation, the health status of the tunnel operation status can be automatically scored based on multi-source information fusion, thereby improving the response speed of tunnel safety evaluation, saving the labor cost of traditional maintenance and safety evaluation, improving the efficiency of civil engineering construction, and facilitating operation and maintenance.

In one example, please refer to Figures 3 and 4. This implementation combines the above-mentioned embodiment method with a newly built tunnel as an example. The tunnel is 390 meters long, designed as a single-hole four-lane tunnel, with a clear height of 5 meters, a clear width of 18.25 meters, and a maximum burial depth of 76 meters. The tunnel section is mainly fine-grained biotite granite, and the rock mass ranges from relatively complete to relatively broken, with many fracture zones and broken zones, and complex geological conditions. The tunnel construction adopts the double-side wall pilot pit method and the middle partition wall method for excavation, and uses smooth blasting technology and pre-grouting and other measures to ensure construction safety and quality. The surrounding rock level is mainly grade III and IV, and locally grade V, especially in the tunnel entrance and exit sections, the surrounding rock is grade V, mainly residual slope accumulation layer and fully weathered granite, with loose structure and susceptible to flood scouring. Therefore, it is necessary to strengthen the interception and drainage measures of surface water. According to the geological survey and drilling results, the tunnel site area is rich in groundwater. The presence of groundwater reduces the physical and mechanical properties of the rock mass, which has a certain impact on the stability of the cave wall rock mass and tunnel construction. Through a systematic health status evaluation model, the structure and function of the tunnel are continuously monitored and evaluated, taking into account factors such as geological conditions, construction quality and operation management, in order to ensure the long-term safety and reliability of the tunnel during operation. The data collected on site mainly comes from regular manual inspections, automated monitoring equipment installed on site, etc. The model is applied to the risk assessment of the tunnel, including: i) establishing a high-risk target model based on the TOPSIS method, ii) verifying the established model, and iii) risk identification and sensitivity analysis.

According to the monitoring plan, 96 measuring points including anchor axial force, internal displacement, groundwater level, contact pressure, steel frame internal force, primary and secondary lining internal force, vault settlement and convergence, tunnel environment and other indicators were deployed on site. Before risk analysis, the collected data needs to be preprocessed. In addition, other forms of data from risk sources are collected, such as safety and construction logs and accident handling records. Combined with the actual situation of the tunnel, multi-source risk information data is determined:

Geological conditions: The surrounding rock formations along the tunnel include residual slope accumulation layer and fully weathered granite, medium weathered granite with fragmented structure, medium weathered granite with fragmented mosaic structure, medium weathered granite with fragmented structure, and residual slope accumulation layer and fully weathered granite. From the perspective of the surrounding rock state, these geological conditions have the characteristics of low strength, developed cracks, and uneven settlement, especially at the entrance and exit of the tunnel, which may cause the tunnel to face problems such as structural deformation, leakage, and local instability during operation. Therefore, three influencing factors are determined: position in the tunnel (X1) and surrounding rock grade (X2).

Hydraulic factors: A high groundwater level will increase the risk of leakage in the tunnel structure and the instability of the foundation, thus endangering the overall safety of the tunnel. The local groundwater level is high and the rainfall is abundant, so the groundwater level (X3) is taken as an influencing factor.

Operation monitoring: In order to monitor the health status of the tunnel during operation, a large number of sensors are designed and deployed, focusing on the internal forces and deformations of the structure. For the tunnel structure, the sensors pay more attention to the anchor axial force (X4), lining internal force (X5), arch crown settlement (X6), steel support stress (X7), arch waist convergence (X8), and tunnel wall vibration (X9).

Human factors. The management and control of human factors are also very important, with the main focus on maintenance management specifications (X10), operation management professionalism (X11), traffic flow and load control (X12), data management and analysis (X13), and prevention of sabotage (X14). Among them, maintenance management specifications require regular inspections and timely repairs; operation management professionalism emphasizes operating specifications and emergency response capabilities; traffic flow and load control is to avoid overloaded operations; prevention of sabotage includes monitoring and management of illegal acts; data management and analysis uses scientific data collection and analysis to timely discover and deal with potential problems to ensure the long-term healthy operation of the tunnel.

Random factors: Random factors are often unpredictable and sudden. The main concerns include traffic accidents (X15) and natural disasters (X16). Among them, traffic accidents, especially collisions of heavy vehicles, may cause direct impact and damage to the tunnel structure; natural disasters such as earthquakes, floods and landslides will cause serious damage to the tunnel structure and function. The unpredictability and suddenness of these random factors require tunnel managers to have good emergency response and risk management capabilities to respond to and mitigate their impact in a timely manner.

The data of risk factors come from different sources. First, the measurement data of X1, X2 and X3 were obtained through geological survey reports. Then, the relevant data of X4 to X9 were collected through on-site automated monitoring equipment. The data of X10 to X14 were collected through on-site surveys of operating units and evaluation of traffic data. Among these factors, some are measurable, while others are based on surveys and judgments. The influencing factors of excavated tunnel operation safety are shown in Figure 3.

Furthermore, in combination with the tunnel operation safety assessment method based on multi-source risk factors of the above embodiment, the distances from the risk factors to the positive ideal solution (PIS) and the negative ideal solution (NIS) are calculated. The relative proximity index (RCCI) value of the factor is calculated by the formula. The ranking results are shown in Table (3), and the RCCI radar chart of each indicator is shown in Figure 4.

Table (3) shows the ranking results of risk factors

Then select the first six key factors and determine the quantitative evaluation model of different factors. The evaluation method for vibration response is: first, calculate the average daily increase rate of vibration amplitude within one month through continuous on-site monitoring for one month. According to experience, set ten times the increase rate as the warning threshold, and the vibration response score calculation formula is:

in, is the current tunnel vibration amplitude change rate, is the rate of change of the initial vibration amplitude. Due to the lack of in-depth research, this evaluation method is highly empirical and needs to be further refined in the development of scoring standards.

The scoring method for changes in tunnel settlement and convergence is similar to that for vibration, and is calculated using the following formulas:

The quantitative scoring formula for tunnel settlement changes is:

The quantitative scoring formula for tunnel convergence change is:

In the formula, is the current daily settlement rate of the tunnel, is the initial convergence rate of the tunnel; and are the warning coefficients, determined by the experience of engineers, and in this case are taken as six and five respectively; is the maximum daily convergence rate of the tunnel, The initial convergence rate of the tunnel. The groundwater level is pre-set with a maximum water level and a minimum water level, and the water head difference between the current water level and the maximum water level is measured by a water level meter to score. It is calculated as follows:

In the formula, is the preset maximum water level, is the preset minimum water level. is the current preset water level. Human damage and traffic accidents are random events. Experts score the tunnel health according to the degree of the on-site events to obtain the health score of the corresponding indicators, and perform weighted average according to the expert confidence index.

Finally, the RCCI of the corresponding six indicators is normalized, and the final evaluation score of tunnel safety is obtained by combining the previous scores. The results of RCCI normalization are: X9-0.265, X14-0.196, X3-0.15, X6-0.139, X15-0.130, X8-0.119. The health status score of the current tunnel operation safety is obtained by multiplying each indicator by the weight: 92.2 points.

Please refer to FIG. 5 , which shows a tunnel operation safety assessment system 200 based on multi-source risk factors provided by this embodiment. The tunnel operation safety assessment system 200 based on multi-source risk factors includes:

An acquisition module 210 is configured to acquire multi-source information data that affects the health status of the tunnel during operation, wherein the multi-source information data includes geological conditions, human factors, and random factors;

A first determination module 220 is configured to perform a single analysis on the multi-source information data based on a plurality of methods to determine the importance of each type of information, wherein the plurality of methods include domain expert evaluation;

The first data processing module 230 is configured to perform a difference elimination analysis on the importance degree to obtain the multi-source comprehensive evaluation weights of the corresponding risk factors, including constructing a summary group decision matrix based on the evaluation information of the domain experts and determining the weights of the risk factors, constructing a weighted summary group decision matrix based on the weights of the risk factors and the summary group decision matrix, determining a positive ideal solution and a negative ideal solution according to the weighted summary group decision matrix, determining the distance between the risk factor and the positive ideal solution and the negative ideal solution according to the positive ideal solution and the negative ideal solution, and obtaining the multi-source comprehensive evaluation weights;

A second determination module 240 is configured to sort the multi-source comprehensive evaluation weights and determine the core risk factor of the tunnel in combination with the complexity of the site requirements;

The second data processing module 250 is configured to build a corresponding quantitative assessment model according to the core risk factor type, and output the indicator health score of each core risk factor based on the quantitative assessment model, wherein the quantitative assessment model includes quantitative scoring of changes in vibration response, tunnel settlement and convergence, wherein:

The quantitative scoring formula for tunnel vibration response is:

The quantitative scoring formula for tunnel settlement changes is:

The quantitative scoring formula for tunnel convergence change is:

In the formula, is the current tunnel vibration amplitude change rate, is the initial vibration amplitude change rate, is the current daily settlement rate of the tunnel, is the initial settlement rate of the tunnel; and is the warning factor, is the maximum daily convergence rate of the tunnel, The initial convergence rate of the bit tunnel;

The third data processing module 260 is configured to build a tunnel operation health scoring model, input the health score of each indicator and the corresponding multi-source comprehensive evaluation weight into the scoring model to obtain the tunnel operation safety and health status assessment result.

In some embodiments, based on the same inventive concept, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the steps of the tunnel operation safety assessment method based on multi-source risk factors as described in any of the above embodiments.

In some embodiments, based on the same inventive concept, a computer-readable storage medium is also provided, on which computer program instructions are stored. When the program instructions are executed by a processor, the steps of the tunnel operation safety assessment method based on multi-source risk factors provided in the above embodiment are implemented.

The terms "first", "second", "third", etc. in the specification and claims of the present application and the drawings are used to distinguish different objects rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a series of steps or units are included, or optionally, steps or units not listed are included, or optionally, other steps or units inherent to these processes, methods, products or devices are included.

Only the part relevant to the present application is shown in the accompanying drawings, but not all of the content. Before discussing the exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processing or methods depicted as flow charts. Although the flow chart describes each operation (or step) as a sequential process, many of the operations therein can be implemented in parallel, concurrently or simultaneously. In addition, the order of each operation can be rearranged. When its operation is completed, the process can be terminated, but it can also have additional steps not included in the accompanying drawings. The process can correspond to a method, function, procedure, subroutine, subprogram, etc.

The terms "component", "module", "system", "unit", etc. used in this specification are used to represent computer-related entities, hardware, firmware, a combination of hardware and software, software, or software in execution. For example, a unit can be, but is not limited to, a process running on a processor, a processor, an object, an executable file, an execution thread, a program, and/or distributed between two or more computers. In addition, these units can be executed from various computer-readable media having various data structures stored thereon. Units can communicate through local and/or remote processes, for example, based on signals having one or more data packets (e.g., data from a second unit interacting with another unit in a local system, a distributed system, and/or a network. For example, the Internet interacts with other systems via signals).

In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "illustrative embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials, or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example.

Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Mentioning "embodiment" in this article means that the specific features, structures or characteristics described in conjunction with the embodiment may be included in at least one embodiment of the present embodiment application. The appearance of this phrase in various positions in the specification is not necessarily the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It can be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

Although the embodiments of the present application have been shown and described, those skilled in the art will appreciate that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present application, and that the scope of the present application is defined by the claims and their equivalents.

Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the disclosure disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary techniques in the art that are not disclosed in the present application. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present application are indicated by the following claims.

Claims (10)

1. A tunnel operation safety assessment method based on multi-source risk factors, characterized by comprising: Obtain multi-source information data that affects the health status of the tunnel during operation; Comprehensively evaluate the importance of indicators of the multi-source information data based on multiple methods to determine the importance of each type of information, wherein the multiple methods include evaluation by domain experts; Performing a difference elimination analysis on the importance levels to obtain multi-source comprehensive evaluation weights of corresponding risk factors; Sorting the multi-source comprehensive evaluation weights and determining the core risk factors of the tunnel in combination with the complexity of site requirements; Building a corresponding quantitative assessment model according to the core risk factor type, and outputting the indicator health score of each core risk factor based on the quantitative assessment model; A health scoring model for the tunnel operation period is established, and the health score of each indicator and the corresponding multi-source comprehensive evaluation weight are input into the scoring model to obtain the assessment results of the safe and healthy status of tunnel operation. 2. A tunnel operation safety assessment method based on multi-source risk factors according to claim 1, characterized in that the importance of indicators of the multi-source information data is comprehensively evaluated based on multiple methods to determine the importance of each type of information, and the multiple methods include field expert evaluation, including: The confidence of the expert evaluation in the field is evaluated based on the expert confidence index, wherein the expert confidence index calculation formula is: In the formula, is the evaluation ability index of the mth expert, is the subjective reliability index of the mth expert; Determining the relative importance of the domain expert's evaluation of the risk factor based on the confidence level of the domain expert's evaluation; The degree of importance of each type of information is determined based on domain expert evaluation of different relative importance. 3. A tunnel operation safety assessment method based on multi-source risk factors according to claim 2, characterized in that the evaluation by domain experts based on different relevant importances to determine the importance of various types of information includes: Construct a fuzzy number corresponding to the relative importance of domain experts, and assign the weights of experts based on the fuzzy number, where: The fuzzy number expression is: The weight expression is: In the formula, represents the important membership degree evaluated by the kth expert, Indicates that the k-th expert has an unimportant membership, It represents the hesitation between the kth expert's evaluation of importance and unimportance. 4. A tunnel operation safety assessment method based on multi-source risk factors according to claim 2 or 3, characterized in that the importance of each type of information is determined by evaluating by experts in the field based on different relevant importances, and further comprising: Based on the evaluation results provided by each expert, an importance evaluation matrix is constructed to compare the different influencing factors of the target. The importance evaluation matrix expression is: In the formula, is the importance evaluation matrix, Factors that affect tunnel health: It is the fuzzy evaluation number determined by the k-th domain expert for the i-th influencing factor at the j-th level. 5. A tunnel operation safety assessment method based on multi-source risk factors according to claim 1, characterized in that the step of performing a difference elimination analysis on the importance levels to obtain a multi-source comprehensive evaluation weight of the corresponding risk factors comprises: Constructing a summary group decision matrix based on the evaluation information of domain experts and determining the weights of risk factors; constructing a weighted summary group decision matrix based on the weights of the risk factors and the summary group decision matrix; Determining a positive ideal solution and a negative ideal solution according to the weighted summary group decision matrix; According to the positive ideal solution and the negative ideal solution, the distance between the risk factor and the positive ideal solution and the negative ideal solution is determined to obtain the multi-source comprehensive evaluation weight, wherein the multi-source comprehensive evaluation weight includes a relative proximity index value of the risk factor. 6. A tunnel operation safety assessment method based on multi-source risk factors according to claim 5, characterized in that the distance between the risk factor and the positive ideal solution and the negative ideal solution is determined according to the positive ideal solution and the negative ideal solution to obtain the multi-source comprehensive evaluation weight, including: Based on the formula determining a first distance between the risk factor and the positive ideal solution; Based on the formula determining a second distance between the risk factor and the negative ideal solution; In the formula, is the first distance, is the second distance, n is the number of importance levels, and are the membership and non-membership of the positive ideal solution, respectively. and are the membership and non-membership of the negative ideal solution, respectively. is the hesitation degree of the positive ideal solution, is the hesitation degree of the negative ideal solution, It represents the weighted evaluation importance of the i-th influencing factor at the j-th level. Indicates the membership degree of the i-th influencing factor at the j-th level that the weighted evaluation is not important, It represents the hesitation degree of importance or unimportance of the i-th influencing factor at the j-th level. 7. According to claim 1, a tunnel operation safety assessment method based on multi-source risk factors is characterized in that the tunnel operation health scoring model is constructed, and each of the indicator health scores and the corresponding multi-source comprehensive evaluation weights are input into the scoring model to obtain the tunnel operation safety and health status assessment results, including: The tunnel operation health scoring model is constructed based on the factor weight weighted average method; Based on the tunnel operation period health scoring model, the comprehensive evaluation weight is normalized and combined with the indicator health score to obtain the final health score J, where: The final health score J is expressed as: In the formula, represents the comprehensive evaluation weight of the i-th normalized key factor, It represents the indicator health score of the i-th key factor, and n represents the total number of selected key factors. 8. A tunnel operation safety assessment system based on multi-source risk factors, characterized by comprising: An acquisition module is configured to acquire multi-source information data that affects the health status of the tunnel during operation, wherein the multi-source information data includes geological conditions, human factors, and random factors; A first determination module is configured to perform a single analysis on the multi-source information data based on a plurality of methods to determine the importance of each type of information, wherein the plurality of methods include domain expert evaluation; A first data processing module is configured to perform a difference elimination analysis on the importance degree to obtain a multi-source comprehensive evaluation weight of the corresponding risk factor, which includes constructing a summary group decision matrix based on the evaluation information of domain experts and determining the weight of the risk factor, constructing a weighted summary group decision matrix based on the weight of the risk factor and the summary group decision matrix, determining a positive ideal solution and a negative ideal solution according to the weighted summary group decision matrix, determining the distance between the risk factor and the positive ideal solution and the negative ideal solution according to the positive ideal solution and the negative ideal solution, and obtaining the multi-source comprehensive evaluation weight; A second determination module is configured to sort the multi-source comprehensive evaluation weights and determine the core risk factor of the tunnel in combination with the complexity of the site requirements; The second data processing module is configured to build a corresponding quantitative assessment model according to the core risk factor type, and output the indicator health score of each core risk factor based on the quantitative assessment model, wherein the quantitative assessment model includes quantitative scoring of changes in vibration response, tunnel settlement and convergence, wherein: The quantitative scoring formula for tunnel vibration response is: The quantitative scoring formula for tunnel settlement changes is: The quantitative scoring formula for tunnel convergence change is: In the formula, is the current tunnel vibration amplitude change rate, is the initial vibration amplitude change rate, is the current daily settlement rate of the tunnel, is the initial settlement rate of the tunnel; and is the warning factor, is the maximum daily convergence rate of the tunnel, The initial convergence rate of the bit tunnel; The third data processing module is configured to build a health scoring model for the tunnel operation period, input the health score of each indicator and the corresponding comprehensive evaluation weight into the scoring model to obtain the tunnel operation safety and health status assessment results. 9. An electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can perform the steps of the tunnel operation safety assessment method based on multi-source risk factors described in any one of claims 1-7. 10. A computer-readable storage medium having computer program instructions stored thereon, characterized in that when the computer program instructions are executed by a processor, the steps of the tunnel operation safety assessment method based on multi-source risk factors described in any one of claims 1 to 7 are implemented.