Safety evaluation method and system for highway tunnel

Abstract

The invention relates to the technical field of highway tunnel safety monitoring, and discloses a highway tunnel safety evaluation method and system, and the method comprises the steps of data collection, data processing, state evaluation, safety evaluation, early warning decision making and the like. The method comprises the following steps: firstly, collecting a plurality of monitoring parameters such as lining stress, surrounding rock pressure and traffic flow load, and carrying out normalization processing; then, calculating the weight of the monitoring parameters by adopting a grey correlation analysis method, and classifying the tunnel state data by combining with an improved fuzzy C-means clustering method; and calculating a tunnel dynamic response index, evaluating a tunnel safety state, and performing dynamic risk evaluation and early warning strategy optimization based on the final risk index R. By monitoring and evaluating the structural safety state of the highway tunnel in real time, potential safety hazards can be found in time, a scientific basis is provided for a tunnel management and maintenance department, and the driving safety of the highway tunnel is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of highway tunnel safety monitoring, and in particular to a highway tunnel safety evaluation method and system. Background Art

[0002] As an important part of transportation infrastructure, the structural safety and operational stability of highway tunnels directly affect the safety and efficiency of road traffic. Since tunnels are affected by multiple factors such as geological conditions, construction quality, operating environment and traffic load, they are prone to safety hazards such as surrounding rock deformation, lining cracking, leakage, and structural stress changes. Existing tunnel safety evaluation methods usually rely on a single monitoring indicator or an evaluation method based on fixed weights. They lack a comprehensive analysis of the coupling of multiple factors and are difficult to accurately reflect the real-time health status of tunnel structures. At the same time, the existing early warning strategies are relatively simple and difficult to dynamically adjust according to different risk levels, which affects the accuracy and effectiveness of safety management.

[0003] Therefore, there is an urgent need for a highway tunnel safety evaluation method that combines multi-parameter monitoring, intelligent analysis and adaptive optimization to improve the identification accuracy of tunnel safety status and risk prevention and control capabilities. Summary of the invention

[0004] In view of this, the present invention proposes a safety evaluation method and system for highway tunnels, aiming to achieve real-time monitoring and comprehensive evaluation of the safety status of highway tunnel structures by integrating multiple monitoring means and applying advanced data analysis algorithms.

[0005] This paper proposes a safety assessment method for highway tunnels, including:

[0006] Collect monitoring parameters related to tunnel safety and normalize the collected monitoring parameters; wherein the monitoring parameters include lining stress, anchor axial force, surrounding rock pressure, tunnel sidewall vibration, arch settlement, surrounding rock deformation, air humidity, temperature gradient, traffic load effect and vibration acceleration response;

[0007] The weights of various monitoring parameters are calculated by grey correlation analysis, and the correlation degree of the weights is calculated; the tunnel status data is classified by improved fuzzy C-means clustering; the tunnel dynamic response index is calculated, and the tunnel safety status is evaluated based on the tunnel dynamic response index, the tunnel safety evaluation level is obtained and output, and early warning information is provided according to the safety evaluation level;

[0008] Among them, the improvements of fuzzy C-means clustering include:

[0009] Introducing a dynamic fuzzy index adjustment strategy to automatically optimize the fuzzy factor according to data distribution;

[0010] Combine the weight information of each indicator to adjust the Euclidean distance;

[0011] Add a noise point identification mechanism to reduce or redistribute the weight of abnormal data points;

[0012] Improved termination conditions are used to avoid overfitting or local convergence.

[0013] Preferably, the normalization of the monitoring parameters adopts the range normalization method, and the calculation formula is as follows:

[0014] ;

[0015] Among them, X i Indicates the normalized index value; X i Represents the original monitoring parameters; X max and X min Indicates the maximum and minimum values ​​of the original monitoring parameter indicators.

[0016] Preferably, the grey correlation analysis method is used to calculate the weight of each monitoring parameter, and the grey correlation coefficient calculation formula is as follows:

[0017] ;

[0018] Where X0(k) represents the reference sequence; X i (k) represents the comparison sequence; ρ represents the resolution coefficient, which ranges from 0 to 1.

[0019] Preferably, the comprehensive weight of the monitoring indicators is calculated based on the grey correlation coefficient:

[0020] ;

[0021] Among them, w i Represents the weight of the monitoring indicator; m represents the time dimension of the monitoring data.

[0022] Preferably, the tunnel dynamic response index is calculated by combining the normalized value and weight of the monitoring data:

[0023] ;

[0024] Where TDRI represents the tunnel dynamic response index; α i represents the linear weight coefficient; β i represents the quadratic nonlinear correction coefficient; γ ij represents the cross-impact factor; X i Indicates the normalized index value.

[0025] Preferably, the tunnel safety evaluation level is calculated based on the tunnel dynamic response index, and the safety evaluation level is divided as follows:

[0026] When TDRI ≤ 0.3, the safety assessment level is classified as level 1, i.e. safe;

[0027] When 0.3<TDRI≤0.6, the safety assessment level is classified as Level 2, i.e. normal;

[0028] When 0.6<TDRI≤0.8, the safety assessment level is divided into three levels, namely, warning;

[0029] When 0.8<TDRI, the safety assessment level is divided into level 4, i.e. dangerous.

[0030] Preferably, in the improved fuzzy C-means clustering, the clustering objective function is as follows:

[0031] ;

[0032] Where J represents the clustering objective function; u ij Indicates the degree of membership of data point i to cluster center j; d ij represents the weighted Euclidean distance between data point i and cluster center j; m represents the dynamic fuzzy factor; N represents the total number of data points.

[0033] Preferably, the early warning strategy is adjusted by combining the tunnel dynamic response index and the fuzzy C-means clustering results:

[0034] ;

[0035] Among them, R represents the final risk index; P i represents the monitoring parameter risk factor; Q j Indicates the influencing factor of external environmental factors; δ j Represents the weight of external environment impact.

[0036] Preferably, the risk warning strategy is optimized based on the final risk index R, including:

[0037] When R≤0.3, maintain the current monitoring frequency and conduct regular assessments;

[0038] When 0.3<R≤0.6, increase the monitoring frequency and focus on the changing trend;

[0039] When 0.6<R≤0.8, the early warning mechanism is activated, inspections are strengthened and safety measures are adjusted;

[0040] When R>0.8, the emergency response plan is activated, including traffic control, support reinforcement and further risk investigation.

[0041] The present invention also proposes a road tunnel safety evaluation system for implementing the above-mentioned road tunnel safety evaluation method. The road tunnel safety evaluation system comprises:

[0042] A data acquisition module, configured to collect monitoring parameters related to tunnel safety in real time and perform normalization processing on the monitoring parameters;

[0043] The data processing module is configured to calculate the weight of each monitoring parameter based on the grey correlation analysis method and perform correlation calculation;

[0044] a state assessment module configured to classify tunnel state data using an improved fuzzy C-means clustering method and calculate a tunnel dynamic response index;

[0045] A safety evaluation module is configured to evaluate the safety status of the tunnel according to the tunnel dynamic response index, calculate the final risk index R, and output the safety evaluation level;

[0046] The early warning decision module is configured to perform dynamic risk assessment, optimize early warning strategies, and adjust monitoring plans based on the final risk index R;

[0047] The display and control module is configured to output tunnel safety status and risk warning information, and work with the safety management system to implement corresponding safety measures.

[0048] Compared with the prior art, the present invention has the following beneficial effects:

[0049] Comprehensive assessment of tunnel safety status: The grey correlation analysis method is used to calculate the weights of each monitoring parameter, and combined with the improved fuzzy C-means clustering method, accurate classification of the tunnel safety status can be achieved to improve assessment accuracy.

[0050] Introducing dynamic response index calculation: By calculating the tunnel dynamic response index (TDRI), the time-varying characteristics of the monitoring data are comprehensively considered to reflect the overall stability of the tunnel structure and improve the scientific nature of risk assessment.

[0051] Dynamic optimization of early warning strategy: Based on the final risk index R, the tunnel safety status is dynamically evaluated, and the risk early warning strategy is optimized accordingly to make monitoring and management measures more accurate and efficient.

[0052] Intelligent safety management: Through the implementation of the highway tunnel safety evaluation system, the automation of data collection, analysis, early warning and control is realized, the level of intelligent tunnel safety management is improved, and the need for manual intervention is reduced.

[0053] Enhance tunnel operation safety: Through real-time monitoring and dynamic early warning, the response speed to sudden risks can be improved, the possibility of safety accidents can be reduced, and the long-term operation stability of highway tunnels can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0055] Figure 1 A flow chart of a safety assessment method for a highway tunnel according to the present invention;

[0056] Figure 2 It is a functional block diagram of the safety assessment method system for highway tunnels of the present invention. DETAILED DESCRIPTION

[0057] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art. It should be noted that, in the absence of conflict, the embodiments of the present invention and the features described in the embodiments can be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0058] See also Figure 1 This embodiment provides a safety assessment method for a highway tunnel, comprising:

[0059] Collect monitoring parameters related to tunnel safety and normalize the collected monitoring parameters; wherein the monitoring parameters include lining stress, anchor axial force, surrounding rock pressure, tunnel sidewall vibration, arch settlement, surrounding rock deformation, air humidity, temperature gradient, traffic load effect and vibration acceleration response;

[0060] The weights of various monitoring parameters are calculated by grey correlation analysis, and the correlation degree of the weights is calculated; the tunnel status data is classified by improved fuzzy C-means clustering; the tunnel dynamic response index is calculated, and the tunnel safety status is evaluated based on the tunnel dynamic response index, the tunnel safety evaluation level is obtained and output, and early warning information is provided according to the safety evaluation level;

[0061] Among them, the improvements of fuzzy C-means clustering include:

[0062] Introducing a dynamic fuzzy index adjustment strategy to automatically optimize the fuzzy factor according to data distribution;

[0063] Combine the weight information of each indicator to adjust the Euclidean distance;

[0064] Add a noise point identification mechanism to reduce or redistribute the weight of abnormal data points;

[0065] Improved termination conditions are used to avoid overfitting or local convergence.

[0066] It can be seen that this embodiment proposes a safety assessment method for a highway tunnel, and the specific steps are as follows:

[0067] First, various monitoring parameters related to tunnel safety are collected, including but not limited to lining stress, anchor axial force, surrounding rock pressure, tunnel sidewall vibration, arch settlement, surrounding rock deformation, air humidity, temperature gradient, traffic load effect, and vibration acceleration response. The collected data needs to be normalized to ensure data consistency and comparability;

[0068] Next, the weights of the above monitoring parameters are calculated using the grey correlation analysis method, and the correlation analysis is performed based on these weights. In addition, the improved fuzzy C-means clustering algorithm is used to classify the tunnel status data. By calculating the dynamic response index of the tunnel, the safety status of the tunnel can be evaluated. According to the evaluation results, the safety evaluation level of the tunnel can be determined, and the corresponding early warning information can be output accordingly so that necessary safety measures can be taken;

[0069] In terms of the improvement of the fuzzy C-means clustering algorithm, this embodiment introduces a dynamic fuzzy index adjustment strategy, which can automatically adjust the fuzzy factor according to the distribution of data, thereby optimizing the clustering effect;

[0070] At the same time, combined with the weight information of each indicator, the traditional Euclidean distance calculation method was adjusted to better reflect the impact of different indicators on clustering results;

[0071] In addition, this method also adds a noise point identification mechanism, which can identify abnormal data points and reduce or redistribute the weights of these data points to reduce the interference of abnormal data on clustering results;

[0072] Finally, an improved termination condition is used to control the iterative process of the clustering algorithm, which effectively avoids the problem of overfitting or local convergence, thereby improving the accuracy and reliability of the clustering results.

[0073] It can be understood that this embodiment provides a comprehensive and detailed highway tunnel safety assessment method, which not only takes into account a variety of monitoring parameters related to tunnel safety, but also conducts in-depth analysis and processing of monitoring data through a series of advanced algorithms and technical means, such as grey correlation analysis, improved fuzzy C-means clustering algorithm, etc. The application of these algorithms and technical means not only improves the accuracy and reliability of tunnel safety assessment, but also provides strong data support for subsequent tunnel maintenance and management. In addition, the method also has good adaptability and flexibility, and can perform targeted safety assessments according to different conditions and needs of the tunnel, thereby ensuring the safety and stability of tunnel operation. Therefore, the method has broad application prospects and promotion value in the field of highway tunnel safety assessment.

[0074] In some embodiments of the present application, the normalization of the monitoring parameters adopts the range normalization method, and the calculation formula is as follows:

[0075] ;

[0076] Among them, X i Indicates the normalized index value; X i Represents the original monitoring parameters; X max and X min Indicates the maximum and minimum values ​​of the original monitoring parameter indicators.

[0077] It can be seen that this embodiment uses the range normalization method to deal with the normalization problem of monitoring parameters. This method uses a specific calculation formula to achieve data standardization. In the specific calculation method, X i represents the normalized index value, while the original data is represented by X i In addition, X max and X min They represent the maximum and minimum values ​​of the indicator in all the data.

[0078] It can be understood that the extreme difference normalization method adopted in this embodiment is not only simple and easy, but also can effectively convert data to the same scale, so as to facilitate subsequent data analysis and processing. The application of this normalization method further enhances the practicality and operability of the highway tunnel safety evaluation method provided by this embodiment. In practical applications, staff can conveniently use this method to normalize the monitoring parameters related to tunnel safety, laying a solid foundation for subsequent safety evaluation work. At the same time, the highway tunnel safety evaluation method provided by this embodiment also has a high level of automation and intelligence, and can realize real-time monitoring and dynamic evaluation of the tunnel safety status. This not only greatly improves the efficiency and accuracy of tunnel safety evaluation, but also provides a strong guarantee for the safe operation of the tunnel. In summary, the highway tunnel intelligent monitoring and evaluation method provided by this embodiment has the advantages of being comprehensive, meticulous, accurate, and reliable, and has broad application prospects and promotion value in the field of highway tunnel safety evaluation.

[0079] In some embodiments of the present application, the grey correlation analysis method is used to calculate the weight of each monitoring parameter, and the grey correlation coefficient calculation formula is as follows:

[0080] ;

[0081] Where X0(k) represents the reference sequence; X i (k) represents the comparison sequence; ρ represents the resolution coefficient, which ranges from 0 to 1.

[0082] It can be seen that when the grey correlation analysis method is used to calculate the weights of each monitoring parameter in this embodiment, the reference sequence X0(k) and the comparison sequence Xi(k) are first determined. The reference sequence usually represents an ideal state or an expected target value, while the comparison sequence is the actual monitored data. The calculation of the grey correlation coefficient involves the resolution coefficient ρ, which ranges from 0 to 1. The size of the resolution coefficient will affect the calculation result of the grey correlation degree, and is usually set according to actual conditions and experience. Through the application of the grey correlation analysis method, this embodiment can accurately calculate the weights of each monitoring parameter when evaluating the safety status of the tunnel, thereby ensuring the objectivity and scientificity of the safety evaluation. In addition, the grey correlation analysis method also has the advantages of simple calculation and intuitive results, which makes the method highly operational and practical in practical applications. In this embodiment, the application of the grey correlation analysis method not only improves the accuracy of the tunnel safety evaluation, but also provides strong data support for subsequent tunnel maintenance and management.

[0083] It can be understood that the intelligent monitoring and evaluation method for highway tunnels provided in this embodiment realizes a comprehensive, detailed, accurate and reliable evaluation of the safety status of the tunnel by comprehensively using a variety of advanced technical means and analysis methods. This method not only has a high level of automation and intelligence, but also has strong adaptability and flexibility, and can perform targeted safety evaluation according to different conditions and needs of the tunnel. Therefore, this method has broad application prospects and promotion value in the field of safety evaluation of highway tunnels, and will provide a strong guarantee for the safe operation of highway tunnels.

[0084] In some embodiments of the present application, the comprehensive weight of the monitoring index is calculated based on the grey correlation coefficient:

[0085] ;

[0086] Among them, w i Represents the weight of the monitoring indicator; m represents the time dimension of the monitoring data.

[0087] It can be seen that this embodiment fully considers the grey correlation coefficient and the time dimension of the monitoring data when calculating the comprehensive weight of the monitoring indicators. Specifically, wi represents the weight of a certain monitoring indicator, and m represents the time dimension of the monitoring data, that is, the changes in the data at different time points are considered. Through comprehensive consideration of the grey correlation coefficient and the time dimension of the monitoring data, this embodiment can more accurately calculate the comprehensive weight of each monitoring indicator when evaluating the safety status of the tunnel. This weight calculation method not only improves the accuracy of the safety evaluation, but also makes the evaluation results more in line with the actual situation. In actual applications, staff can pay more attention to those monitoring indicators that have a greater impact on the safety status of the tunnel based on these weight information, so as to take corresponding maintenance and management measures in time to ensure the safe operation of the tunnel.

[0088] It can be understood that the intelligent monitoring and evaluation method for highway tunnels provided in this embodiment fully considers the grey correlation and time dimension of the data in calculating the comprehensive weight of the monitoring indicators, improves the accuracy and reliability of the safety evaluation, and provides a strong guarantee for the safe operation of highway tunnels.

[0089] In some embodiments of the present application, the tunnel dynamic response index is calculated by combining the normalized value and weight of the monitoring data:

[0090] ;

[0091] Where TDRI represents the tunnel dynamic response index; α i represents the linear weight coefficient; β i represents the quadratic nonlinear correction coefficient; γ ijrepresents the cross-impact factor; X i Indicates the normalized index value.

[0092] It can be seen that this embodiment takes multiple factors into consideration when calculating the tunnel dynamic response index. TDRI is an indicator of the tunnel dynamic response index, and its calculation involves the linear weight coefficient α i , quadratic nonlinear correction coefficient β i and the cross-effect factor γ ij The introduction of these coefficients and factors aims to more comprehensively reflect the impact of monitoring data on the dynamic response of the tunnel. Linear weight coefficient α i represents the relative importance of each monitoring index in evaluating the tunnel dynamic response, and the quadratic nonlinear correction coefficient β i It is used to further modify the index value to more accurately reflect its contribution to the tunnel dynamic response. ij The interaction between different monitoring indicators is considered to evaluate the safety status of the tunnel more comprehensively.

[0093] It is understandable that, by comprehensively considering these coefficients and factors, this embodiment can more accurately calculate the tunnel dynamic response index, thereby achieving an accurate assessment of the tunnel safety status. In practical applications, the staff can take appropriate measures in a timely manner to ensure the safe operation of the tunnel according to the size of the tunnel dynamic response index. This calculation method that comprehensively considers multiple factors not only improves the accuracy of the safety evaluation, but also provides strong data support for subsequent tunnel maintenance and management.

[0094] In some embodiments of the present application, the tunnel safety evaluation level is calculated based on the tunnel dynamic response index, and the safety evaluation level is divided into the following categories:

[0095] When TDRI ≤ 0.3, the safety assessment level is classified as level 1, i.e. safe;

[0096] When 0.3<TDRI≤0.6, the safety assessment level is classified as Level 2, i.e. normal;

[0097] When 0.6<TDRI≤0.8, the safety assessment level is divided into three levels, namely, warning;

[0098] When 0.8<TDRI, the safety assessment level is divided into level 4, i.e. dangerous.

[0099] It can be seen that this embodiment realizes the quantitative evaluation of the tunnel safety status by setting a clear correspondence between the tunnel dynamic response index and the safety evaluation level. Specifically, when the tunnel dynamic response index TDRI is less than or equal to 0.3, the safety status of the tunnel is judged to be level one, that is, the safety status is good and does not require too much attention; when TDRI is between 0.3 and 0.6, the safety evaluation level is level two, indicating that the tunnel is in a normal state, but regular monitoring and maintenance are still required; when TDRI is between 0.6 and 0.8, the safety evaluation level is upgraded to level three, that is, the early warning state, at which time it is necessary to strengthen the monitoring of the tunnel and prepare to take corresponding maintenance measures; and when TDRI is greater than 0.8, the safety evaluation level reaches level four, that is, the dangerous state, and emergency measures must be taken immediately to ensure the safe operation of the tunnel.

[0100] It can be understood that the safety evaluation level classification method based on the tunnel dynamic response index in this embodiment not only improves the accuracy and operability of the safety evaluation, but also provides a clear guiding direction for the maintenance and management of the tunnel, which helps to timely discover and resolve potential safety hazards and ensure the long-term safe operation of highway tunnels.

[0101] In some embodiments of the present application, in the improved fuzzy C-means clustering, the clustering objective function is as follows:

[0102] ;

[0103] Where J represents the clustering objective function; u ij Indicates the degree of membership of data point i to cluster center j; d ij represents the weighted Euclidean distance between data point i and cluster center j; m represents the dynamic fuzzy factor; N represents the total number of data points.

[0104] It can be seen that in this embodiment, in the improved fuzzy C-means clustering algorithm, by optimizing the clustering objective function J, a more accurate division of data points is achieved. ij As the degree of membership of data point i to cluster center j, its value reflects the degree to which the data point belongs to a certain cluster; and d ij It represents the weighted Euclidean distance between data point i and cluster center j. The introduction of this distance makes the clustering result more consistent with the actual distribution of the data. The setting of dynamic fuzzy factor m further enhances the flexibility and adaptability of the algorithm, enabling the clustering process to better handle ambiguity and uncertainty. As an identifier of the total number of data points, N plays an important role in the clustering objective function. It ensures that the algorithm can maintain high efficiency and accuracy when processing large amounts of data.

[0105] It can be understood that the improved fuzzy C-means clustering algorithm adopted in this embodiment not only improves the accuracy and stability of clustering, but also provides a powerful tool for subsequent tunnel safety status analysis. By clustering the monitoring data, the correlation and difference between different monitoring indicators can be more clearly identified, thereby providing a more scientific basis for the safety evaluation and maintenance of the tunnel. In practical applications, this clustering analysis method can be combined with other safety evaluation methods to form a complete highway tunnel safety evaluation system, providing a strong guarantee for the long-term safe operation of the tunnel.

[0106] In some embodiments of the present application, the early warning strategy is adjusted by combining the tunnel dynamic response index and the fuzzy C-means clustering result:

[0107] ;

[0108] Among them, R represents the final risk index; P i represents the monitoring parameter risk factor; Q j Indicates the influencing factor of external environmental factors; δ j Represents the weight of external environment impact.

[0109] It can be seen that this embodiment takes into account the tunnel dynamic response index, fuzzy C-means clustering results and multiple risk factors when adjusting the early warning strategy. R is used as the identifier of the final risk index, and its calculation involves the monitoring parameter risk factor P i , the influencing factors of external environmental factors Q j And the external environment impact weight δ j This method of taking multiple factors into consideration aims to more comprehensively reflect the safety status and risk level of the tunnel. Monitoring parameter risk factor P i represents the contribution of each monitoring indicator in assessing tunnel risk, while the influencing factor Q j The influence of the external environment of the tunnel on the safety status is taken into account, such as geological conditions, climate conditions, etc. External environment impact weight δ j It is used to weight external environmental factors to more accurately reflect their impact on the safety status of the tunnel.

[0110] In actual application, the staff can flexibly adjust the early warning strategy according to the size of the final risk index R. When the R value is high, it means that the safety risk of the tunnel is high and emergency measures need to be taken immediately for intervention; when the R value is low, the frequency of monitoring and maintenance can be appropriately relaxed to improve work efficiency. This early warning strategy adjustment method based on risk index not only improves the pertinence and operability of safety evaluation, but also provides a more scientific decision-making basis for tunnel maintenance and management.

[0111] In addition, this embodiment further refines the adjustment of the early warning strategy by combining the fuzzy C-means clustering results. The results of cluster analysis can help staff more clearly identify the correlation and differences between different monitoring indicators, so as to formulate more specific early warning measures for different clusters. For example, for monitoring indicators with higher risks in certain clusters, their monitoring and evaluation can be strengthened to ensure that potential safety hazards are discovered and resolved in a timely manner.

[0112] In summary, the intelligent monitoring and evaluation method and system for highway tunnels provided in this embodiment fully consider the grey correlation and time dimension of data, multiple risk factors and cluster analysis results in calculating the comprehensive weight of monitoring indicators, tunnel dynamic response index and adjusting early warning strategies, thereby improving the accuracy and reliability of safety evaluation and providing a strong guarantee for the safe operation of highway tunnels.

[0113] In some embodiments of the present application, the risk warning strategy is optimized based on the final risk index R, including:

[0114] When R≤0.3, maintain the current monitoring frequency and conduct regular assessments;

[0115] When 0.3<R≤0.6, increase the monitoring frequency and focus on the changing trend;

[0116] When 0.6<R≤0.8, the early warning mechanism is activated, inspections are strengthened and safety measures are adjusted;

[0117] When R>0.8, the emergency response plan is activated, including traffic control, support reinforcement and further risk investigation.

[0118] It can be seen that this embodiment also adopts a refined management approach in terms of risk warning strategy optimization. When the final risk index R is less than or equal to 0.3, it means that the safety risk of the tunnel is at a low level, so the current monitoring frequency can be maintained and regular evaluations can be conducted to ensure that the operation status of the tunnel is always kept within a safe and controllable range. When the R value is between 0.3 and 0.6, although the safety risk is still within an acceptable range, it has shown a certain upward trend. Therefore, it is necessary to appropriately increase the monitoring frequency and focus on the changing trends of various monitoring indicators in order to promptly discover and deal with potential safety hazards. When the R value further rises to between 0.6 and 0.8, it means that the safety risk of the tunnel is already high, and the early warning mechanism must be immediately activated, the inspection efforts must be strengthened, and the safety measures must be adjusted according to the actual situation to ensure the safety of the tunnel operation. When the R value is greater than 0.8, it means that the safety risk of the tunnel is already extremely serious, and the emergency response plan must be immediately activated, including measures such as implementing traffic control, strengthening support and reinforcement, and conducting further risk investigations to minimize the possibility of safety accidents. This risk warning strategy optimization method based on the final risk index R not only improves the pertinence and effectiveness of safety management, but also provides strong support for the long-term safe operation of the tunnel. In actual application, the staff can flexibly adjust the monitoring and maintenance plan according to the size of the final risk index R to ensure that the operation status of the tunnel is always maintained at the best level.

[0119] See also Figure 2 This embodiment further proposes a road tunnel safety evaluation system, which is used to implement the above-mentioned road tunnel safety evaluation method. The road tunnel safety evaluation system includes:

[0120] A data acquisition module, configured to collect monitoring parameters related to tunnel safety in real time and perform normalization processing on the monitoring parameters;

[0121] The data processing module is configured to calculate the weight of each monitoring parameter based on the grey correlation analysis method and perform correlation calculation;

[0122] a state assessment module configured to classify tunnel state data using an improved fuzzy C-means clustering method and calculate a tunnel dynamic response index;

[0123] A safety evaluation module is configured to evaluate the safety status of the tunnel according to the tunnel dynamic response index, calculate the final risk index R, and output the safety evaluation level;

[0124] The early warning decision module is configured to perform dynamic risk assessment, optimize early warning strategies, and adjust monitoring plans based on the final risk index R;

[0125] The display and control module is configured to output tunnel safety status and risk warning information, and work with the safety management system to implement corresponding safety measures.

[0126] It can be seen that the safety evaluation system for highway tunnels in this embodiment realizes comprehensive, real-time and accurate monitoring and evaluation of the safety status of highway tunnels through the collaborative work between various modules. The data acquisition module ensures the real-time and accuracy of the monitoring parameters, providing a reliable basis for subsequent data processing and status evaluation. The data processing module scientifically and reasonably calculates the weights of each monitoring parameter through the gray correlation analysis method, further improving the accuracy of the evaluation. The status evaluation module adopts the improved fuzzy C-means clustering method to carefully classify the tunnel status data, providing strong support for safety evaluation. The safety evaluation module intuitively evaluates the safety status of the tunnel according to the tunnel dynamic response index, and outputs an easy-to-understand safety evaluation level. The early warning decision module dynamically adjusts the early warning strategy and monitoring plan according to the final risk index R, ensuring the timeliness and pertinence of the safety evaluation. The display and control module realizes the visual output of information, and realizes linkage with the safety management system, providing a convenient means of operation for the safety management of the tunnel. In general, the safety evaluation system for highway tunnels in this embodiment has a high degree of automation, intelligence and accuracy, and provides a strong technical support for the safety management of highway tunnels.

[0127] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0128] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0129] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0130] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0131] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A safety assessment method for a highway tunnel, characterized in that: include: Collect monitoring parameters related to tunnel safety and normalize the collected monitoring parameters; wherein the monitoring parameters include lining stress, anchor axial force, surrounding rock pressure, tunnel sidewall vibration, arch settlement, surrounding rock deformation, air humidity, temperature gradient, traffic load effect and vibration acceleration response; The weights of various monitoring parameters are calculated by grey correlation analysis, and the correlation degree of the weights is calculated; the tunnel status data is classified by improved fuzzy C-means clustering; the tunnel dynamic response index is calculated, and the tunnel safety status is evaluated based on the tunnel dynamic response index, the tunnel safety evaluation level is obtained and output, and early warning information is provided according to the safety evaluation level; Among them, the improvements of fuzzy C-means clustering include: Introducing a dynamic fuzzy index adjustment strategy to automatically optimize the fuzzy factor according to data distribution; Combine the weight information of each indicator to adjust the Euclidean distance; Add a noise point identification mechanism to reduce or redistribute the weight of abnormal data points; Improved termination conditions are used to avoid overfitting or local convergence.

2. The safety assessment method for a highway tunnel according to claim 1, characterized in that: The normalization of the monitoring parameters adopts the range normalization method, and the calculation formula is as follows: ； Among them, X i Indicates the normalized index value; X i Represents the original monitoring parameters; X max and X min Indicates the maximum and minimum values ​​of the original monitoring parameter indicators.

3. The safety assessment method for a highway tunnel according to claim 2, characterized in that: The grey correlation analysis method is used to calculate the weight of each monitoring parameter. The grey correlation coefficient calculation formula is as follows: ； Where X0(k) represents the reference sequence; X i (k) represents the comparison sequence; ρ represents the resolution coefficient, which ranges from 0 to 1.

4. The highway tunnel safety assessment method according to claim 3, characterized in that: Calculate the comprehensive weight of monitoring indicators based on the grey correlation coefficient: ； Among them, w i Represents the weight of the monitoring indicator; m represents the time dimension of the monitoring data.

5. The highway tunnel safety assessment method according to claim 4, characterized in that: Combined with the normalized value and weight of the monitoring data, the tunnel dynamic response index is calculated: ； Where TDRI represents the tunnel dynamic response index; α i represents the linear weight coefficient; β i represents the quadratic nonlinear correction coefficient; γ ij represents the cross-impact factor; X i Represents the normalized index value.

6. The highway tunnel safety assessment method according to claim 5, characterized in that: The tunnel safety evaluation level is calculated based on the tunnel dynamic response index, and the safety evaluation level is divided into the following categories: When TDRI ≤ 0.3, the safety assessment level is classified as level 1, i.e. safe; When 0.3<TDRI≤0.6, the safety assessment level is classified as Level 2, i.e. normal; When 0.6<TDRI≤0.8, the safety assessment level is divided into three levels, namely, warning; When 0.8<TDRI, the safety assessment level is divided into level 4, i.e. dangerous.

7. The highway tunnel safety assessment method according to claim 6, characterized in that: In the improved fuzzy C-means clustering, the clustering objective function is as follows: ； Where J represents the clustering objective function; u ij Indicates the degree of membership of data point i to cluster center j; d ij represents the weighted Euclidean distance between data point i and cluster center j; m represents the dynamic fuzzy factor; N represents the total number of data points.

8. The highway tunnel safety assessment method according to claim 7, characterized in that: Combined with the tunnel dynamic response index and fuzzy C-means clustering results, the early warning strategy is adjusted: ； Among them, R represents the final risk index; P i represents the monitoring parameter risk factor; Q j Indicates the influencing factor of external environmental factors; δ j Represents the weight of external environment impact.

9. The highway tunnel safety assessment method according to claim 8, characterized in that: Optimize the risk warning strategy based on the final risk index R, including: When R≤0.3, maintain the current monitoring frequency and conduct regular assessments; When 0.3<R≤0.6, increase the monitoring frequency and focus on the changing trend; When 0.6<R≤0.8, the early warning mechanism is activated, inspections are strengthened and safety measures are adjusted; When R>0.8, the emergency response plan is activated, including traffic control, support reinforcement and further risk investigation.

10. A road tunnel safety assessment system, used to implement the road tunnel safety assessment method according to any one of claims 1 to 9, characterized in that: The highway tunnel safety assessment system comprises: A data acquisition module, configured to collect monitoring parameters related to tunnel safety in real time and perform normalization processing on the monitoring parameters; The data processing module is configured to calculate the weight of each monitoring parameter based on the grey correlation analysis method and perform correlation calculation; a state assessment module configured to classify tunnel state data using an improved fuzzy C-means clustering method and calculate a tunnel dynamic response index; A safety evaluation module is configured to evaluate the safety status of the tunnel according to the tunnel dynamic response index, calculate the final risk index R, and output the safety evaluation level; The early warning decision module is configured to perform dynamic risk assessment, optimize early warning strategies, and adjust monitoring plans based on the final risk index R; The display and control module is configured to output tunnel safety status and risk warning information, and work with the safety management system to implement corresponding safety measures.

Images